INDEX

Explanations

legal terms and details in documents

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orie

-0.70

 millenn

-0.70

aukee

-0.68

uyomi

-0.67

 arena

-0.65

sofar

-0.61

igator

-0.61

fry

-0.61

essee

-0.61

 unnecess

-0.60

POSITIVE LOGITS

 "âĢ¦

0.98

"(

0.81

 "...

0.78

"'

0.78

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.77

 âĹı

0.76

'[

0.75

 Firstly

0.71

""

0.70

wait

0.69

Activations Density 8.823%

legal terms and details in documents

No Comments

No Known Activations