INDEX

Explanations

phrases mentioning the potential for negative consequences or harmful impacts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "cause" and its variations, indicating potential consequences or effects

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

stra

-0.76

atu

-0.75

ian

-0.72

zai

-0.69

zb

-0.68

 Rated

-0.68

iazep

-0.67

ta

-0.66

ature

-0.66

sonian

-0.66

POSITIVE LOGITS

 havoc

1.30

 headaches

1.03

 mayhem

0.97

 trouble

0.97

 confusion

0.96

 unnecessary

0.93

 outbreaks

0.90

 friction

0.90

 panic

0.87

ãĥĨãĤ£

0.87

Activations Density 0.052%

phrases mentioning the potential for negative consequences or harmful impacts

occurrences of the word "cause" and its variations, indicating potential consequences or effects

No Comments

No Known Activations