INDEX

Explanations

strong negative descriptors or situations

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

otos

-0.84

yip

-0.75

etheus

-0.74

glomer

-0.73

allery

-0.73

lasses

-0.71

interstitial

-0.70

ornia

-0.67

umar

-0.67

uilt

-0.67

POSITIVE LOGITS

text

1.06

plain

1.02

 plain

0.93

sheet

0.91

sheets

0.88

cloth

0.85

rolled

0.83

 vanilla

0.81

\\\\\\\\

0.78

ified

0.78

Activations Density 7.336%

strong negative descriptors or situations

No Comments

No Known Activations