INDEX

Explanations

locations and proper nouns related to a person's background or life story

oai_token-act-pair · gpt-3.5-turbo

instances of geographical locations and associated qualifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

":"/

-0.76

osexual

-0.76

 incarn

-0.70

ueller

-0.66

theless

-0.66

 posit

-0.66

adders

-0.65

obin

-0.64

rices

-0.63

ction

-0.63

POSITIVE LOGITS

 Calif

1.10

Ala

1.00

Md

0.99

 Colo

0.98

 County

0.95

 District

0.93

shire

0.91

 Pradesh

0.91

 Berks

0.90

 northwest

0.90

Activations Density 0.140%

locations and proper nouns related to a person's background or life story

instances of geographical locations and associated qualifiers

No Comments

No Known Activations