INDEX

Explanations

the word "winner" and related phrases

oai_token-act-pair · gpt-3.5-turbo

references to winners and winning in competitive contexts

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

senal

-0.76

uli

-0.75

heny

-0.72

ohyd

-0.69

uku

-0.64

 sulf

-0.63

unda

-0.63

resent

-0.62

ependent

-0.62

 clamp

-0.62

POSITIVE LOGITS

 Winner

0.85

 winner

0.85

 prize

0.80

Winner

0.79

 contestant

0.77

 winners

0.75

paces

0.74

stakes

0.73

liness

0.72

 contender

0.71

Activations Density 0.023%

the word "winner" and related phrases

references to winners and winning in competitive contexts

No Comments

No Known Activations