INDEX

Explanations

phrases related to permissions or usage rights

oai_token-act-pair · gpt-3.5-turbo

phrases indicating permission or allowance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ging

-0.77

 Fighter

-0.69

hran

-0.66

LOT

-0.63

Tok

-0.62

 Labyrinth

-0.62

 Ready

-0.61

ged

-0.61

 Bagg

-0.60

performing

-0.60

POSITIVE LOGITS

hap

0.94

onna

0.86

adian

0.85

nard

0.84

weather

0.83

 optionally

0.81

haps

0.81

berra

0.77

afort

0.77

be

0.72

Activations Density 0.055%

phrases related to permissions or usage rights

phrases indicating permission or allowance

No Comments

No Known Activations