INDEX

Explanations

specific mentions of various trophies in a text

oai_token-act-pair · gpt-3.5-turbo

references to various trophies in sports or competitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

occup

-0.71

 diss

-0.66

mer

-0.64

tem

-0.64

 contracting

-0.63

 radical

-0.63

opt

-0.62

 secular

-0.61

 movements

-0.61

mag

-0.61

POSITIVE LOGITS

 Trophy

4.28

 trophy

2.06

 trophies

1.69

phies

1.47

Cup

1.44

 Award

1.28

 Medal

1.22

Tro

1.20

 Medals

1.13

 Heisman

1.12

Activations Density 0.011%

specific mentions of various trophies in a text

references to various trophies in sports or competitions

No Comments

No Known Activations