INDEX

Explanations

personal anecdotes and real-life experiences shared in a writing style

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

lain

-0.75

 lungs

-0.67

 Flavoring

-0.64

 Rumble

-0.63

 pores

-0.63

 banana

-0.63

anx

-0.62

ves

-0.61

 burg

-0.59

 Greenwood

-0.59

POSITIVE LOGITS

ional

1.03

olkien

0.92

hedon

0.80

renheit

0.77

ournals

0.76

REP

0.76

oln

0.72

 Ezra

0.72

ommel

0.70

elman

0.70

Activations Density 8.357%

personal anecdotes and real-life experiences shared in a writing style

No Comments

No Known Activations