INDEX

Explanations

phrases indicating similarity or comparison

oai_token-act-pair · gpt-3.5-turbo

repetitive phrases that indicate similarity or comparison

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

 Stockholm

-0.70

Ã¼

-0.64

RIS

-0.63

ole

-0.62

 Bild

-0.61

uay

-0.60

aceous

-0.59

azon

-0.58

Ãª

-0.58

 bang

-0.58

POSITIVE LOGITS

etheless

0.92

quartered

0.86

 nomine

0.78

æ©Ł

0.77

theless

0.76

ctr

0.76

 minded

0.75

lihood

0.75

wcsstore

0.74

soever

0.74

Activations Density 0.005%

phrases indicating similarity or comparison

repetitive phrases that indicate similarity or comparison

No Comments

No Known Activations