INDEX

Explanations

names or acronyms related to sporting organizations and events

oai_token-act-pair · gpt-3.5-turbo

acronyms and abbreviations related to sports organizations and events

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

veh

-0.81

rou

-0.78

Hof

-0.69

onen

-0.68

rosc

-0.66

var

-0.64

Hem

-0.63

ht

-0.62

fi

-0.62

hra

-0.62

POSITIVE LOGITS

 Classics

0.88

HY

0.79

IFIED

0.75

ODUCT

0.73

eers

0.72

ILLE

0.72

xual

0.69

DX

0.68

ICAN

0.67

 Sorceress

0.66

Activations Density 0.103%

names or acronyms related to sporting organizations and events

acronyms and abbreviations related to sports organizations and events

No Comments

No Known Activations