INDEX

Explanations

mentions of specific locations or organizations

oai_token-act-pair · gpt-3.5-turbo

possessive forms of names and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hari

-0.79

Reviewer

-0.74

aneously

-0.72

sets

-0.71

ËĪ

-0.71

rait

-0.70

set

-0.70

ï¸ı

-0.69

nels

-0.69

Downloadha

-0.69

POSITIVE LOGITS

 Mansion

0.86

 Disease

0.85

 Syndrome

0.78

 Club

0.78

 International

0.76

 Lodge

0.75

 Miracle

0.75

 Sporting

0.74

 Revenge

0.73

 Casino

0.73

Activations Density 0.061%

mentions of specific locations or organizations

possessive forms of names and entities

No Comments

No Known Activations