INDEX

Explanations

locations or entities related to sports teams

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to specific teams, locations, and individuals

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

ugal

-0.77

initely

-0.75

isting

-0.73

axter

-0.72

ista

-0.68

 Emerson

-0.68

 hunger

-0.68

istor

-0.67

ando

-0.66

ists

-0.66

POSITIVE LOGITS

enegger

0.90

creen

0.79

DAY

0.73

lus

0.71

 Boll

0.71

kus

0.67

orage

0.67

mber

0.66

 Squirrel

0.66

vine

0.66

Activations Density 0.048%

locations or entities related to sports teams

proper nouns related to specific teams, locations, and individuals

No Comments

No Known Activations