INDEX

Explanations

phrases related to memories or thoughts coming to mind

oai_token-act-pair · gpt-3.5-turbo

phrases that discuss thoughts or recollections, particularly those beginning with "comes to mind" or similar expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MSG

-0.70

ongyang

-0.69

 Caps

-0.68

achus

-0.63

aldi

-0.62

uphem

-0.62

IQ

-0.62

nic

-0.61

erva

-0.59

alted

-0.59

POSITIVE LOGITS

ãĤ¼

0.75

ç«

0.73

å§«

0.68

éĹ

0.66

lihood

0.66

ONT

0.65

Ðº

0.62

æ©

0.61

steps

0.60

_-_

0.60

Activations Density 0.041%

phrases related to memories or thoughts coming to mind

phrases that discuss thoughts or recollections, particularly those beginning with "comes to mind" or similar expressions

No Comments

No Known Activations