INDEX

Explanations

phrases containing various quotes or statements from different individuals

oai_token-act-pair · gpt-3.5-turbo

phrases indicating something being said or stated by someone

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 metic

-0.84

 unborn

-0.74

 cloning

-0.72

 clones

-0.72

 favor

-0.72

 interns

-0.71

 clitor

-0.70

 grips

-0.68

 spir

-0.68

 favour

-0.68

POSITIVE LOGITS

ï¸ı

1.11

Ther

0.89

----------------------------------------------------------------

0.89

ecause

0.89

conom

0.88

reci

0.87

Because

0.86

Certainly

0.86

TPP

0.86

Likewise

0.85

Activations Density 0.120%

phrases containing various quotes or statements from different individuals

phrases indicating something being said or stated by someone

No Comments

No Known Activations