INDEX

Explanations

names or titles associated with winners or top performers in competitions

oai_token-act-pair · gpt-3.5-turbo

references to champions or championship titles

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iasco

-0.82

iday

-0.75

ftime

-0.75

uld

-0.73

eret

-0.69

kefeller

-0.68

duino

-0.67

ateral

-0.65

nsic

-0.65

ename

-0.64

POSITIVE LOGITS

 boxer

0.80

iors

0.77

 contender

0.76

 challenger

0.75

boards

0.74

 champion

0.73

hip

0.73

 Champion

0.71

aign

0.68

hips

0.66

Activations Density 0.019%

names or titles associated with winners or top performers in competitions

references to champions or championship titles

No Comments

No Known Activations