INDEX

Explanations

phrases related to the act of quitting or giving up

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ANS

-1.13

Catalog

-1.11

Herm

-0.94

inen

-0.94

---------------

-0.93

å¥³

-0.92

 ancest

-0.92

translation

-0.92

 Attribution

-0.92

ammy

-0.91

POSITIVE LOGITS

ters

1.47

 smoking

1.43

ting

1.32

 Smoking

1.09

 Quit

1.05

 quitting

1.02

tering

0.99

 whining

0.94

ts

0.93

 abruptly

0.93

Activations Density 0.279%

phrases related to the act of quitting or giving up

No Comments

No Known Activations