INDEX

Explanations

locations or places where events occurred

oai_token-act-pair · gpt-3.5-turbo

locations mentioned in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

hack

-0.63

ifest

-0.62

iva

-0.62

yp

-0.61

apult

-0.61

ynasty

-0.61

Grade

-0.60

pac

-0.60

 incent

-0.59

tty

-0.59

POSITIVE LOGITS

upon

1.92

 they

1.13

soever

1.12

he

1.03

she

0.92

abouts

0.89

 temperatures

0.81

 there

0.79

it

0.76

 tensions

0.75

Activations Density 0.081%

locations or places where events occurred

locations mentioned in a narrative context

No Comments

No Known Activations