INDEX

Explanations

references to audio equipment and personal narratives, particularly memoirs and autobiographies

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

enegger

-0.74

 Chow

-0.70

eele

-0.63

 Whedon

-0.62

 Webb

-0.62

enance

-0.61

 Hawkins

-0.61

 Pearson

-0.61

LER

-0.59

 Watson

-0.59

POSITIVE LOGITS

 headphones

0.62

 Emin

0.59

ics

0.58

wives

0.57

opus

0.57

0.56

 headphone

0.56

icates

0.55

obook

0.55

necessary

0.55

Activations Density 0.041%

references to audio equipment and personal narratives, particularly memoirs and autobiographies

No Comments

No Known Activations