INDEX

Explanations

locations or cities

oai_token-act-pair · gpt-3.5-turbo

geographical locations and city names

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Moment

-0.59

rious

-0.59

CBI

-0.57

 bandwagon

-0.56

ãĤ¯

-0.55

Ü

-0.55

 brut

-0.55

aspers

-0.54

guy

-0.54

 Ukrainians

-0.53

POSITIVE LOGITS

 Heights

0.93

 Township

0.91

 suburb

0.91

shire

0.88

 township

0.78

 Springs

0.77

 County

0.76

fecture

0.76

town

0.75

 City

0.75

Activations Density 0.236%

locations or cities

geographical locations and city names

No Comments

No Known Activations