INDEX

Explanations

references to sacrifice

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

orders

-0.76

 Hust

-0.68

 Levi

-0.65

NER

-0.64

 Scouting

-0.64

 Cheong

-0.63

Ale

-0.63

 Carl

-0.63

 Ferdinand

-0.62

occ

-0.61

POSITIVE LOGITS

rifice

1.27

 sacrifice

1.24

 sacrifices

1.16

 sacrificed

1.12

 sacrificing

0.97

ificial

0.96

 sacrific

0.95

 Sacrifice

0.91

rament

0.89

 altar

0.76

Activations Density 0.199%

references to sacrifice

No Comments

No Known Activations