INDEX

Explanations

spokespeople in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to spokespersons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

resy

-0.78

undo

-0.76

ozy

-0.76

akespe

-0.75

rament

-0.75

omer

-0.73

ype

-0.71

acca

-0.71

ustom

-0.70

aucus

-0.70

POSITIVE LOGITS

 Anne

1.11

 Marie

1.07

 Louise

1.03

 Nicole

0.99

 Christina

0.94

 Mary

0.93

 Margaret

0.93

 Nina

0.92

 Elizabeth

0.91

 Isabel

0.90

Activations Density 0.051%

spokespeople in various contexts

references to spokespersons

No Comments

No Known Activations