INDEX

Explanations

phrases that indicate upcoming explanations or the necessity of certain concepts in a logical or mathematical context

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

CreateModel

-0.52

jws

-0.48

 rather

-0.46

 romanos

-0.45

Barriers

-0.45

 based

-0.45

Rather

-0.45

 overrun

-0.44

WebServlet

-0.44

 istnieje

-0.44

POSITIVE LOGITS

Geographie

0.63

 <=",

0.61

migrationBuilder

0.60

 utafitiHapana

0.57

用到

0.56

detectChanges

0.54

jande

0.54

 utilisation

0.54

argout

0.53

krankungen

0.53

Activations Density 0.060%

phrases that indicate upcoming explanations or the necessity of certain concepts in a logical or mathematical context

No Comments

No Known Activations