INDEX

Explanations

phrases involving someone mentioned or saying something

oai_token-act-pair · gpt-3.5-turbo

assertive statements or claims related to discussions or conversations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

SPONSORED

-0.85

xon

-0.76

sylvania

-0.71

ocide

-0.70

polit

-0.68

vernment

-0.68

Attorney

-0.66

Republican

-0.66

usalem

-0.65

acerb

-0.65

POSITIVE LOGITS

 that

1.31

that

1.05

 thats

1.04

 THAT

1.04

 "...

0.86

 "âĢ¦

0.80

 they

0.80

:-

0.79

 anecd

0.76

 That

0.76

Activations Density 0.308%

phrases involving someone mentioned or saying something

assertive statements or claims related to discussions or conversations

No Comments

No Known Activations