INDEX

Explanations

phrases related to specific geographic locations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in."

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

CLASSIFIED

-0.57

 convol

-0.54

%%

-0.54

username

-0.53

killed

-0.52

 surpr

-0.51

wagon

-0.51

 lodged

-0.51

ALSE

-0.48

soever

-0.48

POSITIVE LOGITS

 lieu

1.15

 accordance

1.06

 conjunction

1.00

 vitro

1.00

ordinate

0.99

 regards

0.97

clusions

0.92

 order

0.92

 spite

0.92

clus

0.91

Activations Density 0.530%

phrases related to specific geographic locations

occurrences of the word "in."

No Comments

No Known Activations