INDEX

Explanations

descriptions and terms related to different positions in sports teams, particularly in soccer

oai_token-act-pair · gpt-3.5-turbo

references to football management positions and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Bundy

-0.79

 Whitman

-0.77

Zip

-0.76

 Rollins

-0.72

PAX

-0.72

 Appalachian

-0.72

 Navajo

-0.71

 Vanderbilt

-0.71

 Hawai

-0.71

olulu

-0.69

POSITIVE LOGITS

 footballer

1.14

 striker

1.09

England

1.09

ottenham

1.06

Manchester

1.05

Liverpool

1.04

 goalkeeper

1.01

 midfielder

1.00

 fixtures

0.99

 Fifa

0.99

Activations Density 0.226%

descriptions and terms related to different positions in sports teams, particularly in soccer

references to football management positions and related terminology

No Comments

No Known Activations