INDEX

Explanations

mentions of sports players, particularly focusing on their quality or importance

oai_token-act-pair · gpt-3.5-turbo

references to athletes and team players in sports 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

ories

-0.71

anus

-0.69

ombat

-0.67

cgi

-0.66

yss

-0.66

 Newsp

-0.64

isson

-0.63

 Publication

-0.62

 Readers

-0.62

 strang

-0.62

POSITIVE LOGITS

 talent

0.83

 drafted

0.82

 sacrificed

0.80

 talents

0.75

 whom

0.75

who

0.72

 capable

0.71

 possessed

0.71

 coached

0.69

 Scouting

0.67

Activations Density 0.166%

mentions of sports players, particularly focusing on their quality or importance

references to athletes and team players in sports contexts

No Comments

No Known Activations