INDEX

Explanations

phrases related to providing evidence or making claims,

oai_token-act-pair · gpt-3.5-turbo

prepositions and phrases indicating relationships or contexts

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

BuyableInstoreAndOnline

-0.82

 yawn

-0.71

 wiped

-0.65

lyn

-0.63

 Mages

-0.62

 blaze

-0.61

 swell

-0.60

 Minor

-0.59

Nir

-0.59

 bleach

-0.58

POSITIVE LOGITS

©¶æ

0.77

rase

0.76

Ĭ±

0.75

appropriately

0.74

leg

0.70

rompt

0.68

advert

0.66

ivari

0.66

conduct

0.66

vised

0.66

Activations Density 0.253%

phrases related to providing evidence or making claims,

prepositions and phrases indicating relationships or contexts

No Comments

No Known Activations