INDEX

Explanations

phrases related to negative events or situations

oai_token-act-pair · gpt-3.5-turbo

references to negative experiences or outcomes

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

ebus

-0.82

sonian

-0.82

verning

-0.77

racuse

-0.76

TAIN

-0.75

aukee

-0.72

erey

-0.72

tesy

-0.72

£ı

-0.72

ilant

-0.72

POSITIVE LOGITS

 imaginable

0.89

 Karma

0.89

 karma

0.88

 Worse

0.88

 Syndrome

0.88

 inflicted

0.87

 worse

0.84

 plague

0.80

 syndrome

0.80

 havoc

0.80

Activations Density 0.427%

phrases related to negative events or situations

references to negative experiences or outcomes

No Comments

No Known Activations