INDEX

Explanations

phrases indicating additional information or emphasis

oai_token-act-pair · gpt-3.5-turbo

phrases or concepts indicating caveats or additional notes

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

twitch

-0.75

Constructed

-0.74

hard

-0.66

sil

-0.64

arij

-0.63

spot

-0.62

isf

-0.60

shell

-0.59

iminary

-0.59

ophys

-0.59

POSITIVE LOGITS

lihood

0.81

epad

0.68

_>

0.64

 mentioning

0.64

 indexes

0.63

omsday

0.63

DonaldTrump

0.62

 incidentally

0.60

 è£ı

0.60

 imagine

0.59

Activations Density 0.022%

phrases indicating additional information or emphasis

phrases or concepts indicating caveats or additional notes

No Comments

No Known Activations