INDEX

Explanations

postal addresses

oai_token-act-pair · gpt-3.5-turbo

geographical locations and related details

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

nsic

-0.83

xual

-0.83

nsics

-0.77

 blackmail

-0.77

ĸļ

-0.74

 incrim

-0.73

 aliases

-0.73

 favour

-0.71

 alias

-0.70

cules

-0.69

POSITIVE LOGITS

ONSORED

1.08

Includes

0.98

âĸ¬

0.95

OSED

0.94

Located

0.92

 Located

0.89

Population

0.89

Tel

0.86

Opening

0.85

Address

0.84

Activations Density 0.100%

postal addresses

geographical locations and related details

No Comments

No Known Activations