INDEX

Explanations

contact information

oai_token-act-pair · gpt-3.5-turbo

references to contact information or instructions

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

imposed

-0.78

corn

-0.72

orthy

-0.71

 leaps

-0.69

artifacts

-0.68

cott

-0.68

rikes

-0.67

perm

-0.65

ipeg

-0.65

zees

-0.62

POSITIVE LOGITS

ioned

0.78

ASE

0.77

 Vector

0.75

ysis

0.73

kson

0.72

ting

0.71

Us

0.70

him

0.69

ted

0.69

Syl

0.67

Activations Density 0.022%

contact information

references to contact information or instructions

No Comments

No Known Activations