INDEX

Explanations

ideas or opinions expressed by individuals

oai_token-act-pair · gpt-3.5-turbo

phrases expressing skepticism or criticism

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

byss

-0.73

ãĥŁ

-0.68

 Escape

-0.62

ouses

-0.57

 indoors

-0.56

 nearby

-0.55

ãĤ¨ãĥ«

-0.55

 Kinnikuman

-0.55

 Adren

-0.55

irtual

-0.55

POSITIVE LOGITS

0.99

 miscon

0.93

 rhetorical

0.85

 ..."

0.84

 âĢ¦"

0.83

Senator

0.83

 rhetoric

0.83

polit

0.81

 disingen

0.81

 bipartisan

0.79

Activations Density 1.016%

ideas or opinions expressed by individuals

phrases expressing skepticism or criticism

No Comments

No Known Activations