INDEX

Explanations

words related to health or healing, especially ones related to specific organizations or individuals

oai_token-act-pair · gpt-3.5-turbo

the presence of the term "Well" or its variations, particularly in a context related to trust or institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

rely

-0.85

elist

-0.74

âĹ¼

-0.73

illac

-0.70

ļéĨĴ

-0.69

ategory

-0.68

emonic

-0.66

illary

-0.65

esthes

-0.64

NetMessage

-0.62

POSITIVE LOGITS

 Fargo

1.25

esley

1.24

mark

1.05

spring

1.04

marks

0.95

ness

0.94

come

0.91

ington

0.89

brook

0.87

espie

0.87

Activations Density 0.049%

words related to health or healing, especially ones related to specific organizations or individuals

the presence of the term "Well" or its variations, particularly in a context related to trust or institutions

No Comments

No Known Activations