INDEX

Explanations

lists of states and countries

oai_token-act-pair · gpt-3.5-turbo

mentions of U.S. states and countries

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

:(

-0.71

reads

-0.66

ptoms

-0.63

ror

-0.62

worldly

-0.61

 additive

-0.59

 motivation

-0.58

 guiActiveUn

-0.57

 adaptations

-0.57

 murd

-0.57

POSITIVE LOGITS

etc

1.17

etc

0.94

 Moroc

0.90

 Territories

0.79

istan

0.78

 Samoa

0.74

 Halls

0.72

ĪĴ

0.72

Ã£

0.72

 Guam

0.71

Activations Density 0.231%

lists of states and countries

mentions of U.S. states and countries

No Comments

No Known Activations