INDEX

Explanations

words related to choices and decision-making

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_slefr-ajt/2-res_slefr-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aucas

-0.64

alions

-0.63

ãģĨ

-0.62

iltration

-0.61

nard

-0.59

azines

-0.59

farious

-0.59

untled

-0.58

icone

-0.57

rollers

-0.56

POSITIVE LOGITS

Cook

0.67

 Redd

0.62

quickShipAvailable

0.57

 Tanz

0.56

jo

0.56

Var

0.56

 Hels

0.55

ker

0.55

 Daly

0.55

alach

0.54

Activations Density 0.001%

words related to choices and decision-making

No Comments

No Known Activations