INDEX

Explanations

prepositions or prepositional phrases indicating location or direction

oai_token-act-pair · gpt-3.5-turbo

prepositions and phrases indicating relationships or connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AAA

-0.65

 Tribune

-0.59

 priesthood

-0.57

Constructed

-0.57

edar

-0.57

 Artemis

-0.57

 Ballard

-0.54

Ner

-0.53

 Forth

-0.53

cod

-0.52

POSITIVE LOGITS

 beforehand

0.89

 besides

0.87

 anyways

0.87

 nowadays

0.83

.</

0.82

 during

0.77

 anyway

0.75

 BEFORE

0.74

 dearly

0.74

 ðŁĻĤ

0.71

Activations Density 0.200%

prepositions or prepositional phrases indicating location or direction

prepositions and phrases indicating relationships or connections

No Comments

No Known Activations