INDEX

Explanations

names of sports players and statistical information related to sports

oai_token-act-pair · gpt-3.5-turbo

sports-related data and statistics

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

 Feminist

-0.93

 Â®

-0.86

 UNESCO

-0.83

enegger

-0.75

 Capitalism

-0.75

 Quartz

-0.71

 Prohibition

-0.70

 condoms

-0.70

pour

-0.69

 diplom

-0.68

POSITIVE LOGITS

 teammate

1.12

 rookie

1.12

Coach

1.07

 coach

1.05

 rookies

1.00

 Rookie

0.99

 teammates

0.97

 scouting

0.95

 coaches

0.95

 league

0.94

Activations Density 0.283%

names of sports players and statistical information related to sports

sports-related data and statistics

No Comments

No Known Activations