INDEX

Explanations

references to detaining individuals or groups

oai_token-act-pair · gpt-3.5-turbo

terms related to detention and incarceration

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

avascript

-0.66

GD

-0.66

itton

-0.64

hift

-0.63

abba

-0.61

amsung

-0.61

 antioxid

-0.59

Downloadha

-0.59

IDENT

-0.59

 crane

-0.58

POSITIVE LOGITS

ments

1.78

ment

1.77

mentation

1.30

mented

1.25

MENTS

1.21

mental

1.17

MENT

1.05

ings

1.02

ances

0.98

cies

0.97

Activations Density 0.046%

references to detaining individuals or groups

terms related to detention and incarceration

No Comments

No Known Activations