INDEX

Explanations

dates mentioned in text

oai_token-act-pair · gpt-3.5-turbo

references to specific days in a narrative context

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

 VIDEOS

-0.80

éļ

-0.78

plet

-0.73

akia

-0.73

ãģĤ

-0.71

bourg

-0.70

olate

-0.70

ãģķ

-0.70

å§«

-0.69

ierrez

-0.69

POSITIVE LOGITS

lights

0.72

lies

0.71

nings

0.65

 clerk

0.62

liest

0.61

 Judith

0.61

 Theresa

0.61

she

0.59

 Went

0.59

 closest

0.58

Activations Density 0.079%

dates mentioned in text

references to specific days in a narrative context

No Comments

No Known Activations