INDEX

Explanations

comparisons in quantity, often focusing on the concept of "fewer."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

shire

-0.60

Mut

-0.58

Draft

-0.57

wine

-0.56

NB

-0.56

agency

-0.56

raised

-0.54

 Immun

-0.53

MO

-0.53

 Literary

-0.52

POSITIVE LOGITS

 than

1.05

 Than

0.75

than

0.71

bies

0.68

 calories

0.67

een

0.66

 digits

0.62

 pesky

0.62

 bells

0.61

 copies

0.61

Activations Density 7.579%

comparisons in quantity, often focusing on the concept of "fewer."

No Comments

No Known Activations