INDEX

Explanations

locations or settings related to different activities or events

oai_token-act-pair · gpt-3.5-turbo

locations or places mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

laus

-0.81

auts

-0.70

unct

-0.62

iton

-0.62

uctor

-0.62

anche

-0.61

ritis

-0.60

anson

-0.59

ortality

-0.59

rences

-0.58

POSITIVE LOGITS

 periphery

0.88

 doorstep

0.83

 occasions

0.76

 pedest

0.74

 basis

0.71

 behalf

0.71

 shelf

0.70

 alone

0.66

eve

0.65

top

0.65

Activations Density 0.347%

locations or settings related to different activities or events

locations or places mentioned in the text

No Comments

No Known Activations