INDEX

Explanations

events related to changes in a person's status or situation

oai_token-act-pair · gpt-3.5-turbo

words related to transitions and changes in status or position

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

acan

-0.68

 Berman

-0.62

EB

-0.62

ÃŁ

-0.62

 Shooter

-0.61

nic

-0.60

struct

-0.60

kb

-0.59

 Barron

-0.59

 Saud

-0.59

POSITIVE LOGITS

ishment

0.92

 date

0.92

 spree

0.91

 announcement

0.83

ãĥ¯

0.76

href

0.75

mate

0.75

 journey

0.75

Reloaded

0.72

 demise

0.71

Activations Density 0.166%

events related to changes in a person's status or situation

words related to transitions and changes in status or position

No Comments

No Known Activations