INDEX

Explanations

phrases that start with "Ċ" and end with a numerical value, possibly related to a specific encoding or formatting within the text

oai_token-act-pair · gpt-3.5-turbo

numeric values or high cardinality items in text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

heit

-0.86

boro

-0.74

abouts

-0.60

utical

-0.59

ython

-0.58

ounce

-0.57

rad

-0.56

ophy

-0.55

 lifes

-0.53

 equip

-0.52

POSITIVE LOGITS

Likewise

0.85

Meanwhile

0.82

Furthermore

0.82

Nonetheless

0.81

Interestingly

0.81

However

0.80

PHOTOS

0.80

Nevertheless

0.80

Ironically

0.79

Moreover

0.78

Activations Density 0.629%

phrases that start with "Ċ" and end with a numerical value, possibly related to a specific encoding or formatting within the text

numeric values or high cardinality items in text

No Comments

No Known Activations