INDEX

Explanations

references to statements or ideas postulated for consideration or acceptance

oai_token-act-pair · gpt-3.5-turbo

mentions of "propositions" or similar concepts related to proposals or ideas

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

gel

-0.79

adder

-0.73

emetery

-0.73

assetsadobe

-0.72

eway

-0.66

estones

-0.65

dos

-0.64

gio

-0.64

annis

-0.63

gan

-0.63

POSITIVE LOGITS

 proposition

1.31

ually

1.07

 propositions

1.04

eering

0.94

naire

0.93

eers

0.91

selves

0.80

terday

0.79

ual

0.76

enance

0.75

Activations Density 0.011%

references to statements or ideas postulated for consideration or acceptance

mentions of "propositions" or similar concepts related to proposals or ideas

No Comments

No Known Activations