INDEX

Explanations

commands and programming-related text

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

 construct

-0.51

 Construct

-0.48

Cop

-0.48

Hol

-0.47

 influence

-0.46

 cush

-0.45

Cop

-0.45

************

-0.44

 altered

-0.44

 remod

-0.44

POSITIVE LOGITS

interstitial

0.71

inburgh

0.67

adeon

0.66

culosis

0.64

raltar

0.64

roit

0.63

ãĥį

0.61

ushima

0.60

nces

0.58

umenthal

0.58

Activations Density 33.109%

commands and programming-related text

No Comments

No Known Activations