INDEX

Explanations

quotations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "told," indicating reported speech or quotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

isol

-0.78

 sidx

-0.76

reci

-0.70

fet

-0.68

agement

-0.67

aband

-0.66

adesh

-0.66

 ILCS

-0.65

few

-0.65

mun

-0.65

POSITIVE LOGITS

 reporters

1.17

 HuffPost

0.93

me

0.91

IPS

0.89

us

0.89

 CNBC

0.86

CNN

0.86

 Politico

0.84

 BuzzFeed

0.83

ABC

0.82

Activations Density 0.042%

quotations

instances of the word "told," indicating reported speech or quotations

No Comments

No Known Activations