INDEX

Explanations

instances of pride or confidence expressed in a positive manner

oai_token-act-pair · gpt-3.5-turbo

expressions of pride or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

externalActionCode

-0.75

 Annotations

-0.73

gers

-0.67

 Sequence

-0.67

vae

-0.64

Reviewer

-0.63

ente

-0.62

LR

-0.62

ebin

-0.60

Interest

-0.59

POSITIVE LOGITS

 proudly

0.91

 displayed

0.88

 proclaim

0.81

ãĤ©

0.78

 proclaiming

0.76

 boasted

0.72

 boldly

0.71

 displaying

0.69

 disguised

0.69

 proclaimed

0.68

Activations Density 0.021%

instances of pride or confidence expressed in a positive manner

expressions of pride or emphasis

No Comments

No Known Activations