INDEX

Explanations

words related to racing

oai_token-act-pair · gpt-3.5-turbo

references to racing as a sport or activity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ividual

-0.84

asure

-0.75

asures

-0.74

ochond

-0.72

iture

-0.71

orative

-0.70

awk

-0.70

xus

-0.68

Wan

-0.68

roma

-0.68

POSITIVE LOGITS

 racing

1.05

 racer

0.83

enegger

0.75

nell

0.75

 Racer

0.74

 motorcycles

0.72

ball

0.71

 race

0.71

 races

0.70

cars

0.69

Activations Density 0.016%

words related to racing

references to racing as a sport or activity

No Comments

No Known Activations