INDEX

Explanations

phrases related to ethics and morality

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, specifically periods

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

 paran

-0.63

 pockets

-0.59

 cradle

-0.58

 accelerating

-0.57

 notebooks

-0.57

 collapsed

-0.56

 misconceptions

-0.56

 patriarch

-0.55

acle

-0.55

 supplements

-0.54

POSITIVE LOGITS

actionDate

0.90

."

0.87

-.

0.80

\-

0.79

mil

0.75

certain

0.73

Ku

0.71

sit

0.69

until

0.69

################################

0.69

Activations Density 0.018%

phrases related to ethics and morality

punctuation marks, specifically periods

No Comments

No Known Activations