INDEX

Explanations

phrases expressing strong negative emotions or criticisms towards others

oai_token-act-pair · gpt-3.5-turbo

expressions of regret or disgrace towards individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 livest

-0.79

llan

-0.75

 stabilization

-0.75

Downloadha

-0.74

nels

-0.73

minster

-0.72

perature

-0.71

atonin

-0.70

combe

-0.69

ernand

-0.69

POSITIVE LOGITS

 taxpayers

0.84

ãĤ®

0.82

ĳå£«

0.81

 cheated

0.80

 victims

0.80

 inflicted

0.79

da

0.77

 humanity

0.73

 anyone

0.73

 shareholders

0.72

Activations Density 0.298%

phrases expressing strong negative emotions or criticisms towards others

expressions of regret or disgrace towards individuals or groups

No Comments

No Known Activations