INDEX

Explanations

words related to relationships between people or entities

oai_token-act-pair · gpt-3.5-turbo

references to strong emotional experiences or attachments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĵĺ

-0.80

 Brist

-0.55

 Corpus

-0.52

mx

-0.52

 Adren

-0.52

Engineers

-0.49

 Thanksgiving

-0.49

 âĢº

-0.48

 corpor

-0.48

Zac

-0.47

POSITIVE LOGITS

ividual

0.58

miah

0.58

obyl

0.57

idon

0.57

ichick

0.55

eport

0.55

lings

0.55

osuke

0.54

rite

0.53

rafted

0.52

Activations Density 3.184%

words related to relationships between people or entities

references to strong emotional experiences or attachments

No Comments

No Known Activations