INDEX

Explanations

phrases related to events or actions happening very quickly

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "as soon as"

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

İĭ

-0.76

senal

-0.73

cipline

-0.71

pel

-0.70

atively

-0.70

aden

-0.65

warm

-0.65

ativity

-0.63

initely

-0.62

orius

-0.62

POSITIVE LOGITS

aneously

0.90

 thereafter

0.84

 realised

0.75

idious

0.72

 realized

0.67

 afterwards

0.66

eners

0.65

 Meter

0.64

 lear

0.63

ened

0.62

Activations Density 0.012%

phrases related to events or actions happening very quickly

instances of the phrase "as soon as"

No Comments

No Known Activations