INDEX

Explanations

words related to sports titles

oai_token-act-pair · gpt-3.5-turbo

references to titles 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Spicer

-0.68

oidal

-0.68

pmwiki

-0.65

 Gork

-0.65

 Spice

-0.63

esthetic

-0.62

velength

-0.62

ajor

-0.62

iasco

-0.61

 Lindsey

-0.61

POSITIVE LOGITS

holder

0.91

manship

0.88

 contender

0.88

marks

0.85

title

0.85

 titles

0.83

holders

0.83

 title

0.83

ifications

0.80

 holder

0.79

Activations Density 0.016%

words related to sports titles

references to titles in competitive contexts

No Comments

No Known Activations