INDEX

Explanations

terms related to rotation and movement

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hig

-0.70

ãģį

-0.70

éĹĺ

-0.65

iary

-0.64

aii

-0.63

 Drinking

-0.63

ħĭ

-0.62

abba

-0.62

externalActionCode

-0.61

eteria

-0.60

POSITIVE LOGITS

rot

0.86

 rotated

0.83

ting

0.82

rosc

0.79

lav

0.79

wheel

0.78

Rot

0.77

lob

0.76

ULAR

0.76

 helic

0.75

Activations Density 0.261%

terms related to rotation and movement

No Comments

No Known Activations