INDEX

Explanations

words related to replacing or replacing things

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

raq

-1.14

hest

-0.81

arta

-0.77

vern

-0.77

ern

-0.75

WA

-0.75

saf

-0.75

keyes

-0.73

zag

-0.72

zai

-0.72

POSITIVE LOGITS

ments

0.94

 obsolete

0.94

mented

0.80

orate

0.79

itute

0.78

 bulbs

0.78

 redundant

0.77

ative

0.77

atives

0.76

utions

0.74

Activations Density 8.742%

words related to replacing or replacing things

No Comments

No Known Activations