INDEX

Explanations

words related to locations or geographical regions

oai_token-act-pair · gpt-3.5-turbo

terms related to geographical or contextual provenance, specifically focusing on domestic, local, national, and international aspects

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

eer

-0.77

ger

-0.75

 Parenthood

-0.73

 Times

-0.67

 beginnings

-0.66

tones

-0.65

Ing

-0.64

Klu

-0.63

 League

-0.62

mails

-0.62

POSITIVE LOGITS

 speaking

1.00

 Speaking

0.83

 minded

0.81

 produced

0.81

 planted

0.80

 detonated

0.79

 challeng

0.79

 formulated

0.77

 tuned

0.77

hesive

0.77

Activations Density 0.057%

words related to locations or geographical regions

terms related to geographical or contextual provenance, specifically focusing on domestic, local, national, and international aspects

No Comments

No Known Activations