INDEX

Explanations

Twitter handles

oai_token-act-pair · gpt-3.5-turbo

Twitter handles or mentions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Takeru

-0.75

 Norwich

-0.72

 favors

-0.69

 specificity

-0.68

 jars

-0.65

 exorc

-0.64

 nasal

-0.63

 fixtures

-0.63

 suffering

-0.63

 favor

-0.62

POSITIVE LOGITS

username

1.12

realDonaldTrump

0.98

Official

0.97

thereal

0.94

Coach

0.92

ANI

0.91

Real

0.90

#$

0.86

stats

0.85

deck

0.84

Activations Density 0.022%

Twitter handles

Twitter handles or mentions

No Comments

No Known Activations