INDEX

Explanations

phrases related to negative judgments or strong disapproval

oai_token-act-pair · gpt-3.5-turbo

negative descriptors related to poor conditions or failures

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

NetMessage

-0.85

ahime

-0.73

imov

-0.72

ced

-0.71

hibition

-0.70

wi

-0.70

 Flavoring

-0.69

cule

-0.68

thood

-0.67

chn

-0.67

POSITIVE LOGITS

 depl

1.20

orable

0.88

abby

0.86

ancies

0.72

ãģį

0.71

aste

0.69

ue

0.69

 lamented

0.68

enance

0.67

 veter

0.65

Activations Density 0.007%

phrases related to negative judgments or strong disapproval

negative descriptors related to poor conditions or failures

No Comments

No Known Activations