INDEX

Explanations

expressions of pride or positivity

oai_token-act-pair · gpt-3.5-turbo

instances of the word "proudly" and similar expressions of pride or prominence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Annotations

-0.77

vae

-0.75

 Sequence

-0.72

ergus

-0.66

ebin

-0.65

nesota

-0.63

 Killer

-0.61

EMS

-0.59

ests

-0.59

 Rapp

-0.59

POSITIVE LOGITS

 proudly

0.89

 proclaim

0.87

 displayed

0.82

 proclaiming

0.80

 boasted

0.80

 proclaimed

0.75

ãĤ©

0.74

 boasting

0.73

 disguised

0.71

roud

0.68

Activations Density 0.008%

expressions of pride or positivity

instances of the word "proudly" and similar expressions of pride or prominence

No Comments

No Known Activations