INDEX

Explanations

mentions of specific geographical locations and political figures

oai_token-act-pair · gpt-3.5-turbo

references to geographical locations and their political status

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 thereof

-0.77

Specifically

-0.76

 favors

-0.73

 favored

-0.71

 favoring

-0.70

 utilizes

-0.67

 utilizing

-0.67

 labeled

-0.66

 therein

-0.66

 ______

-0.65

POSITIVE LOGITS

 inquest

0.91

 paed

0.88

incial

0.88

 counselling

0.87

 Surrey

0.86

orkshire

0.85

 apologise

0.84

 Auckland

0.84

 Yorkshire

0.83

 apologised

0.83

Activations Density 1.996%

mentions of specific geographical locations and political figures

references to geographical locations and their political status

No Comments

No Known Activations