INDEX

Explanations

phrases and terms related to the long-term implications or consequences of actions

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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

Reviewed

-0.61

inia

-0.60

illian

-0.58

å§«

-0.57

atche

-0.57

osponsors

-0.56

uala

-0.55

othing

-0.55

cius

-0.55

ropolitan

-0.54

POSITIVE LOGITS

est

0.81

 term

0.76

term

0.70

liest

0.67

 aftermath

0.65

shore

0.62

 side

0.60

 absence

0.60

 pend

0.59

 timeframe

0.58

Activations Density 7.887%

phrases and terms related to the long-term implications or consequences of actions

No Comments

No Known Activations