INDEX

Explanations

verbs or nouns related to mental or physical processes

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

liest

-0.39

 manned

-0.35

 circled

-0.32

 ring

-0.31

etsk

-0.31

osures

-0.30

rikes

-0.30

 strive

-0.30

luster

-0.30

 endeav

-0.29

POSITIVE LOGITS

ļéĨĴ

0.43

 PTSD

0.36

ively

0.36

ional

0.35

 saline

0.35

arians

0.35

HUD

0.35

aldehyde

0.35

ative

0.34

 incoming

0.33

Activations Density 0.525%

verbs or nouns related to mental or physical processes

No Comments

No Known Activations