INDEX

Explanations

instances of the letter 'd' 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

 متعلقه

-0.53

にかけて

-0.51

当時は

-0.46

URIComponent

-0.45

 damals

-0.40

for

-0.40

 рук

-0.40

君子

-0.40

别说

-0.40

ならず

-0.40

POSITIVE LOGITS

fjspx

0.73

 Revel

0.66

PreferredItem

0.64

IBOutlet

0.62

idopsis

0.61

Xna

0.61

ніципалі

0.61

OCD

0.61

 Kimura

0.59

 Cremation

0.59

Activations Density 0.008%

instances of the letter 'd' in various contexts

No Comments

No Known Activations