INDEX

Explanations

terms related to alcohol consumption and alcoholism

oai_token-act-pair · gpt-3.5-turbo

words related to alcoholism and its effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

erva

-0.79

erving

-0.75

trak

-0.74

peer

-0.72

oppers

-0.71

oard

-0.70

hao

-0.69

GV

-0.69

ample

-0.68

©¶æ

-0.68

POSITIVE LOGITS

 alcoholic

1.22

 beverages

1.20

 beverage

1.14

cohol

0.96

 liquor

0.96

 drinks

0.95

 alcohol

0.94

 dehyd

0.93

cir

0.93

 alcoholism

0.90

Activations Density 0.010%

terms related to alcohol consumption and alcoholism

words related to alcoholism and its effects

No Comments

No Known Activations