INDEX

Explanations

contractions indicating negation or denial

oai_token-act-pair · gpt-3.5-turbo

negative language regarding existence or certainty

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

PU

-0.66

 Butt

-0.61

 Relationship

-0.60

 Mechdragon

-0.60

 Species

-0.59

 Draw

-0.57

 face

-0.57

 contractor

-0.57

 maturity

-0.57

dress

-0.56

POSITIVE LOGITS

't

1.30

iting

0.89

geon

0.88

etsk

0.88

tyard

0.86

ited

0.84

tesy

0.82

¹

0.82

ajor

0.81

nas

0.80

Activations Density 0.066%

contractions indicating negation or denial

negative language regarding existence or certainty

No Comments

No Known Activations