INDEX

Explanations

questions about meanings, interpretations, and implications

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

 Pend

-0.65

ttes

-0.62

 diversion

-0.62

tions

-0.62

visors

-0.60

 Paso

-0.57

visor

-0.57

Du

-0.56

Peb

-0.56

court

-0.55

POSITIVE LOGITS

terday

0.69

rawdownloadcloneembedreportprint

0.65

INGS

0.64

ELL

0.63

 goodbye

0.59

Ð»

0.58

pling

0.58

depending

0.57

ASC

0.57

UTF

0.57

Activations Density 5.879%

questions about meanings, interpretations, and implications

No Comments

No Known Activations