INDEX

Explanations

Proper nouns related to political figures and geographical locations

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

ãĤ¢ãĥ«

-0.51

thood

-0.49

CAST

-0.49

angelo

-0.48

cial

-0.47

cially

-0.47

ancial

-0.42

ãĥł

-0.42

rawdownloadcloneembedreportprint

-0.42

onential

-0.42

POSITIVE LOGITS

 Rouge

0.54

obin

0.53

enei

0.51

 Kardashian

0.49

®

0.47

schild

0.47

 Irving

0.46

awi

0.45

yna

0.44

ouri

0.43

Activations Density 12.158%

Proper nouns related to political figures and geographical locations

No Comments

No Known Activations