INDEX

Explanations

the word "Ottawa."

oai_token-act-pair · gpt-3.5-turbo

references to the city of Ottawa and related historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

pmwiki

-0.74

 Scientology

-0.72

-0.70

vous

-0.69

itably

-0.68

âĸ¬

-0.68

 Sunshine

-0.66

nces

-0.65

å£«

-0.65

 Respect

-0.63

POSITIVE LOGITS

obar

1.25

awa

1.09

oms

1.02

olen

0.99

oman

0.97

ahon

0.90

olini

0.87

atell

0.85

rop

0.84

agar

0.84

Activations Density 0.012%

the word "Ottawa."

references to the city of Ottawa and related historical contexts

No Comments

No Known Activations