INDEX

Explanations

news-related words or events mentioned in newspapers or magazines

oai_token-act-pair · gpt-3.5-turbo

instances of news reporting and publication actions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gui

-0.75

 subsistence

-0.72

genic

-0.71

unts

-0.69

 valve

-0.69

band

-0.67

 potency

-0.66

tec

-0.66

gren

-0.65

 plateau

-0.64

POSITIVE LOGITS

 editorial

1.04

 Editorial

0.95

 Newsp

0.93

Reader

0.91

 Readers

0.90

 Investigative

0.88

 publishes

0.87

 headlined

0.85

 editor

0.85

 columnist

0.85

Activations Density 0.512%

news-related words or events mentioned in newspapers or magazines

instances of news reporting and publication actions

No Comments

No Known Activations