INDEX

Explanations

locations, specifically counties and cities, in California

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

 responsiveness

-0.66

ardless

-0.65

dys

-0.65

glers

-0.61

sworth

-0.60

bodied

-0.56

Dys

-0.56

atform

-0.55

 Starr

-0.55

 Dickens

-0.55

POSITIVE LOGITS

å£«

0.84

 Earthqu

0.84

 Unified

0.82

emia

0.74

 Valley

0.73

ienne

0.72

 County

0.72

escal

0.70

 Fault

0.69

Gas

0.68

Activations Density 12.160%

locations, specifically counties and cities, in California

No Comments

No Known Activations