INDEX

Explanations

words related to qualities or characteristics

oai_token-act-pair · gpt-3.5-turbo

suffixes indicating a characteristic or state

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

tackle

-0.61

 NOTE

-0.58

 drawer

-0.57

 Lemon

-0.57

 scraping

-0.56

 Absent

-0.56

 Liberties

-0.55

 Dealer

-0.55

 hawk

-0.55

altern

-0.55

POSITIVE LOGITS

opter

0.89

oning

0.89

gment

0.87

omi

0.82

heastern

0.80

rill

0.79

otype

0.78

ements

0.78

otyp

0.78

entials

0.77

Activations Density 0.152%

words related to qualities or characteristics

suffixes indicating a characteristic or state

No Comments

No Known Activations