INDEX

Explanations

the term "second" in various contexts

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Eastwood

-0.77

 Elbe

-0.68

BEA

-0.66

 ſeveral

-0.65

jelaskan

-0.64

 Tommaso

-0.63

Ulf

-0.62

tenham

-0.60

 themſelves

-0.59

 cutest

-0.59

POSITIVE LOGITS

Hauptartikel

0.63

illett

0.59

cleros

0.56

liğ

0.56

 géographie

0.56

'+

0.55

 Merritt

0.54

 bong

0.52

ule

0.52

 gland

0.52

Activations Density 0.011%

the term "second" in various contexts

No Comments

No Known Activations