INDEX

Explanations

references to sports teams from Kansas City in particular

oai_token-act-pair · gpt-3.5-turbo

mentions of Kansas City and its 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

mble

-0.84

bably

-0.84

BOOK

-0.80

thood

-0.79

nces

-0.75

aces

-0.75

 Scotia

-0.73

encers

-0.71

×Ļ×

-0.70

cffffcc

-0.69

POSITIVE LOGITS

 City

1.11

Kansas

0.91

 Kansas

0.89

 Wichita

0.86

oslov

0.83

 Republic

0.82

 Chiefs

0.81

 State

0.81

 Rapids

0.81

 Tornado

0.80

Activations Density 0.013%

references to sports teams from Kansas City in particular

mentions of Kansas City and its sports teams

No Comments

No Known Activations