INDEX

Explanations

references to sources or origins of information

oai_token-act-pair · gpt-3.5-turbo

the preposition "in" frequently used in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aspers

-0.78

DEM

-0.74

lly

-0.72

DragonMagazine

-0.71

DERR

-0.70

ydia

-0.69

ĺħ

-0.68

llor

-0.66

attery

-0.66

ACY

-0.66

POSITIVE LOGITS

 question

0.90

effect

0.89

 totality

0.87

patient

0.78

 conjunction

0.78

 front

0.77

ducers

0.77

liest

0.76

 lieu

0.75

 relation

0.72

Activations Density 0.364%

references to sources or origins of information

the preposition "in" frequently used in various contexts

No Comments

No Known Activations