INDEX

Explanations

specific phrases or patterns related to written text and communication, specifically highlighting mentions of correspondence, publication, and text analysis

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

issance

-0.74

ndum

-0.68

hood

-0.64

most

-0.64

 spokeswoman

-0.62

christ

-0.61

 Counsel

-0.61

bart

-0.60

onsense

-0.60

 Advertisement

-0.60

POSITIVE LOGITS

 concentrated

0.84

 clustered

0.70

 identical

0.68

 crammed

0.68

 equally

0.66

 interchangeable

0.66

 individually

0.66

orted

0.65

 redundant

0.65

ECD

0.64

Activations Density 13.522%

specific phrases or patterns related to written text and communication, specifically highlighting mentions of correspondence, publication, and text analysis

No Comments

No Known Activations