INDEX

Explanations

the word "branch" and variations within technical or organizational contexts

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

 Ukrain

-0.74

vered

-0.66

 Predators

-0.65

izer

-0.61

ËĪ

-0.60

 Gors

-0.60

imar

-0.60

xml

-0.60

 IMAGES

-0.60

ted

-0.59

POSITIVE LOGITS

dale

0.84

illary

0.84

 branches

0.81

ranch

0.80

 branch

0.80

ular

0.78

tip

0.75

ipation

0.74

itect

0.73

zhou

0.72

Activations Density 12.246%

the word "branch" and variations within technical or organizational contexts

No Comments

No Known Activations