INDEX

Explanations

references to specific individuals

oai_token-act-pair · gpt-3.5-turbo

mentions of the pronoun "he."

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

anking

-0.66

 Transactions

-0.65

 Claire

-0.64

requisite

-0.63

earch

-0.63

uy

-0.63

history

-0.63

veyard

-0.62

 Bearing

-0.61

 Girls

-0.61

POSITIVE LOGITS

'd

1.27

eded

1.10

'll

1.08

resy

0.93

 knew

0.92

uristic

0.91

aped

0.90

zbollah

0.89

've

0.86

ctic

0.86

Activations Density 0.344%

references to specific individuals

mentions of the pronoun "he."

No Comments

No Known Activations