INDEX

Explanations

references to names or titles enclosed in quotation marks

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

 lapse

-1.17

 destro

-1.01

 persecut

-0.97

 abduct

-0.96

 answ

-0.95

 recip

-0.93

 recipients

-0.92

 abusers

-0.91

 quantity

-0.91

 deval

-0.89

POSITIVE LOGITS

til

2.10

cause

1.80

tis

1.58

Mech

1.50

-'

1.48

round

1.43

Cause

1.43

Interstitial

1.29

kay

1.26

================================================================

1.24

Activations Density 0.675%

references to names or titles enclosed in quotation marks

No Comments

No Known Activations