INDEX

Explanations

mentions or instances of the word "found"

oai_token-act-pair · gpt-3.5-turbo

phrases indicating personal discoveries or realizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

idium

-0.86

 partic

-0.68

heed

-0.65

 concess

-0.65

istry

-0.64

cius

-0.64

 paced

-0.61

 attendant

-0.60

 Mandatory

-0.60

fue

-0.59

POSITIVE LOGITS

 myself

0.84

ä½¿

0.78

ãĤ¤ãĥĪ

0.77

IU

0.76

ãģ®å

0.76

çīĪ

0.73

Īè

0.70

é¾įå

0.70

Ô

0.69

unn

0.69

Activations Density 0.059%

mentions or instances of the word "found"

phrases indicating personal discoveries or realizations

No Comments

No Known Activations