INDEX

Explanations

phrases related to aggression or actions involving physical harm

oai_token-act-pair · gpt-3.5-turbo

references to the act of removing or eliminating

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

esa

-0.78

hetti

-0.75

BILITY

-0.74

isma

-0.69

gnu

-0.63

ogue

-0.63

ould

-0.61

iets

-0.61

bly

-0.61

Ã®

-0.60

POSITIVE LOGITS

stretched

0.72

ãĥīãĥ©

0.71

 swat

0.69

rage

0.68

 weeds

0.68

ta

0.67

lier

0.66

smart

0.65

doors

0.63

tml

0.62

Activations Density 0.028%

phrases related to aggression or actions involving physical harm

references to the act of removing or eliminating

No Comments

No Known Activations