INDEX

Explanations

mentions of standards or specific criteria being evaluated

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

resent

-0.64

ston

-0.62

lez

-0.59

seat

-0.58

ãĥİ

-0.57

hs

-0.57

noon

-0.56

rontal

-0.55

mer

-0.55

leton

-0.54

POSITIVE LOGITS

 deviations

0.90

 deviation

0.84

 standards

0.76

 bearer

0.70

 compliant

0.67

 governing

0.63

 Compliance

0.61

 Enforcement

0.59

 regulating

0.59

iblings

0.59

Activations Density 15.068%

mentions of standards or specific criteria being evaluated

No Comments

No Known Activations