INDEX

Explanations

phrases related to various football leagues, especially the Bundesliga, Serie A, La Liga, and the Premiership

oai_token-act-pair · gpt-3.5-turbo

references to football leagues and competitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

anim

-0.80

walking

-0.80

patrick

-0.73

dos

-0.73

rider

-0.72

orses

-0.71

pher

-0.71

orah

-0.70

 Rider

-0.69

wal

-0.69

POSITIVE LOGITS

 Bundesliga

1.04

 footballer

0.99

 strugg

0.93

 millenn

0.82

 Liga

0.81

 Serie

0.81

League

0.77

liga

0.77

MX

0.75

ottest

0.75

Activations Density 0.010%

phrases related to various football leagues, especially the Bundesliga, Serie A, La Liga, and the Premiership

references to football leagues and competitions

No Comments

No Known Activations