INDEX

Explanations

words related to condemning or criticizing specific actions or events

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Wonders

-1.29

paio

-1.16

ramid

-1.13

 Solitaire

-1.08

iago

-1.02

eland

-0.99

eah

-0.98

NetMessage

-0.98

aghetti

-0.96

ysc

-0.92

POSITIVE LOGITS

ations

1.14

national

1.12

rities

1.10

 condemning

1.10

 condemn

1.09

 condemns

1.09

urous

1.05

ounces

1.04

ifiable

1.04

 unequivocally

1.03

Activations Density 1.236%

words related to condemning or criticizing specific actions or events

No Comments

No Known Activations