INDEX

Explanations

words related to criticism or evaluating something negatively

oai_token-act-pair · gpt-3.5-turbo

instances of the letter 'r'

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Sons

-0.74

 cardio

-0.66

 hers

-0.64

 EntityItem

-0.64

ROM

-0.64

 Lobby

-0.60

 mine

-0.60

 ours

-0.60

 rope

-0.59

SOS

-0.58

POSITIVE LOGITS

ipples

1.39

ambling

1.33

ifling

1.33

umbling

1.28

agged

1.27

iddle

1.27

attle

1.26

iddles

1.26

haps

1.23

angers

1.23

Activations Density 0.015%

words related to criticism or evaluating something negatively

instances of the letter 'r'

No Comments

No Known Activations