INDEX

Explanations

specific names or entities in a document

oai_token-act-pair · gpt-3.5-turbo

references to authority figures or political elements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Pg

-0.70

-->

-0.69

Scroll

-0.69

 Replay

-0.68

KR

-0.67

 GOODMAN

-0.67

 Doors

-0.66

>>

-0.66

Secondly

-0.63

ouch

-0.63

POSITIVE LOGITS

 consolid

0.80

 indul

0.72

 hypothes

0.69

 pione

0.68

 langu

0.66

 sleek

0.65

 relaxing

0.64

 devoted

0.64

 ambig

0.64

 integrating

0.63

Activations Density 0.586%

specific names or entities in a document

references to authority figures or political elements

No Comments

No Known Activations