INDEX

Explanations

particular words such as "proper" and terms related to measurements and specifications

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

_>

-0.69

hyde

-0.69

âĹı

-0.66

 Lilly

-0.64

acid

-0.62

è¦ļéĨĴ

-0.62

yrs

-0.61

=-=-=-=-

-0.60

ank

-0.60

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

-0.59

POSITIVE LOGITS

tarian

1.19

 functioning

0.98

tarians

0.85

 noun

0.84

bred

0.80

 etiquette

0.75

nsic

0.75

 guiActiveUn

0.73

lly

0.71

iciary

0.70

Activations Density 9.107%

particular words such as "proper" and terms related to measurements and specifications

No Comments

No Known Activations