INDEX

Explanations

mentions of sports teams, especially the Houston Texans

oai_token-act-pair · gpt-3.5-turbo

references to the city of Houston and its associated sports teams

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

lihood

-0.90

DonaldTrump

-0.78

arial

-0.75

BOOK

-0.74

udic

-0.73

thood

-0.73

userc

-0.71

Downloadha

-0.69

chant

-0.69

uchin

-0.69

POSITIVE LOGITS

STON

1.15

 Dynamo

1.12

 Chronicle

1.10

 Texans

1.09

 Rockets

1.07

 Astros

1.05

 Oilers

0.85

ians

0.84

apolis

0.82

sburg

0.82

Activations Density 0.015%

mentions of sports teams, especially the Houston Texans

references to the city of Houston and its associated sports teams

No Comments

No Known Activations