INDEX

Explanations

words related to conveying information or messages

oai_token-act-pair · gpt-3.5-turbo

words associated with communication and conveying messages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

anwhile

-0.68

ussy

-0.66

Bav

-0.64

erenn

-0.62

ADE

-0.61

 judiciary

-0.60

erala

-0.60

FE

-0.60

lymp

-0.60

pire

-0.58

POSITIVE LOGITS

 conveyed

1.16

 convey

1.11

cha

0.83

 conve

0.79

wagon

0.78

soType

0.78

weight

0.73

uron

0.73

wright

0.72

tale

0.71

Activations Density 0.012%

words related to conveying information or messages

words associated with communication and conveying messages

No Comments

No Known Activations