INDEX

Explanations

text related to legal terms or legislative provisions

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

byn

-0.67

abal

-0.58

Tube

-0.52

tube

-0.50

orship

-0.48

umo

-0.48

 UKIP

-0.47

 terr

-0.45

ulet

-0.45

 Ethiopian

-0.45

POSITIVE LOGITS

regulated

0.61

 Â§Â§

0.59

 Definitions

0.58

IFIED

0.57

ãĥĥãĥī

0.56

reference

0.55

İĭ

0.55

 Â§

0.53

ventions

0.52

seq

0.52

Activations Density 13.723%

text related to legal terms or legislative provisions

No Comments

No Known Activations