INDEX

Explanations

non-English characters, potentially in a specific language or encoding

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

illas

-0.69

illa

-0.68

aic

-0.67

eers

-0.67

 logger

-0.66

olves

-0.64

stadt

-0.63

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.61

 chau

-0.59

 levers

-0.58

POSITIVE LOGITS

ħ

0.94

¾

0.85

¼

0.84

Į

0.84

ãģį

0.83

ttp

0.81

İ

0.78

Î±

0.76

Ĩ

0.76

ŀ

0.75

Activations Density 9.747%

non-English characters, potentially in a specific language or encoding

No Comments

No Known Activations