INDEX

Explanations

information related to biological taxa and their habitats

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

 hadn

-0.88

whatever

-0.84

0000000000000000

-0.83

didn

-0.83

funding

-0.79

—-

-0.79

intent

-0.78

interrupted

-0.78

LCS

-0.78

Josh

-0.75

POSITIVE LOGITS

tymology

0.90

 varieties

0.88

 decorative

0.87

 commonly

0.86

orn

0.84

 Zoro

0.83

 elong

0.81

âĵĺ

0.80

 Lanka

0.80

 distinguishes

0.80

Activations Density 24.992%

information related to biological taxa and their habitats

No Comments

No Known Activations