INDEX

Explanations

past tense verbs that suggest completion or accomplishment

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "laid" in various contexts

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

=-=-=-=-=-=-=-=-

-0.75

ities

-0.74

externalActionCode

-0.72

acca

-0.69

ively

-0.68

qua

-0.65

ernaut

-0.64

ivals

-0.63

iles

-0.62

obs

-0.62

POSITIVE LOGITS

sheets

0.84

galitarian

0.83

 laid

0.82

 groundwork

0.81

ndra

0.79

mate

0.79

mination

0.78

 siege

0.76

tons

0.76

hog

0.74

Activations Density 0.013%

past tense verbs that suggest completion or accomplishment

occurrences of the word "laid" in various contexts

No Comments

No Known Activations