INDEX

Explanations

discussions related to legal agreements and intellectual property issues

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FN

-0.74

OHN

-0.71

 Cause

-0.70

 Photographer

-0.69

 Direction

-0.67

Fine

-0.67

 Times

-0.67

Exit

-0.67

 Newsp

-0.67

 Governments

-0.67

POSITIVE LOGITS

cient

0.94

sonian

0.90

tainment

0.89

orical

0.85

ificial

0.84

assing

0.82

efully

0.81

ingly

0.81

arse

0.80

arine

0.79

Activations Density 9.233%

discussions related to legal agreements and intellectual property issues

No Comments

No Known Activations