INDEX

Explanations

parenting and mental health-related phrases

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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

 ticks

-0.10

<-

-0.09

atten

-0.09

 notch

-0.09

 throats

-0.09

MMR

-0.08

uld

-0.08

 skew

-0.08

################################

-0.08

 Layer

-0.08

POSITIVE LOGITS

IFIED

0.11

ordan

0.10

krit

0.08

mble

0.08

ggies

0.08

udic

0.08

cules

0.08

gal

0.08

namese

0.08

amus

0.08

Activations Density 19.561%

parenting and mental health-related phrases

No Comments

No Known Activations