INDEX

Explanations

mentions of famous individuals

oai_token-act-pair · gpt-3.5-turbo

phrases that display rhetorical questioning or uncertainty

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

catentry

-0.87

 util

-0.66

 lapt

-0.63

iHUD

-0.63

cially

-0.62

Applications

-0.61

entimes

-0.60

inding

-0.60

TEXT

-0.59

Qt

-0.57

POSITIVE LOGITS

 goddamn

0.78

 kidding

0.78

 damned

0.77

 damn

0.76

 Pulitzer

0.75

 darn

0.70

 chuckle

0.70

 hypocrisy

0.69

HAHAHAHA

0.69

 bigot

0.68

Activations Density 1.730%

mentions of famous individuals

phrases that display rhetorical questioning or uncertainty

No Comments

No Known Activations