INDEX

Explanations

words related to criticism or judgment

oai_token-act-pair · gpt-3.5-turbo

instances of the word "rid" and its variations, typically associated with extreme or ridiculous situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

enegger

-0.74

arser

-0.70

EEK

-0.68

mpeg

-0.66

 flap

-0.64

ropolitan

-0.62

aic

-0.62

 Spect

-0.61

ODY

-0.60

 STAND

-0.60

POSITIVE LOGITS

ged

1.29

ging

1.24

ges

1.23

gew

1.20

uction

1.18

gewater

1.14

gements

1.13

gment

1.06

gments

1.04

gement

1.04

Activations Density 0.100%

words related to criticism or judgment

instances of the word "rid" and its variations, typically associated with extreme or ridiculous situations

No Comments

No Known Activations