INDEX

Explanations

instances of the phrase "This is."

oai_token-act-pair · gpt-3.5-turbo

repeated phrases indicating a state of being or description within statements

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

luaj

-0.68

soever

-0.68

styles

-0.67

 glances

-0.65

kson

-0.64

chev

-0.64

ievers

-0.64

 stripes

-0.62

IDs

-0.61

opez

-0.60

POSITIVE LOGITS

rael

0.96

 unlikely

0.88

 definitely

0.85

NOT

0.82

not

0.81

 happening

0.81

 likely

0.80

 important

0.79

 supposed

0.78

 abundantly

0.77

Activations Density 0.114%

instances of the phrase "This is."

repeated phrases indicating a state of being or description within statements

No Comments

No Known Activations