INDEX

Explanations

mentions of locations and features related to physical spaces

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

Negative Logits

 local

-0.75

 JpaRepository

-0.60

local

-0.59

 صوتيه

-0.59

 lokal

-0.56

entendre

-0.54

 modern

-0.52

瞰

-0.50

 location

-0.50

gnostic

-0.49

POSITIVE LOGITS

 StatelessWidget

0.67

bootstrapcdn

0.60

 awakeFromNib

0.54

 Shakspeare

0.53

 essendo

0.52

 NUKAT

0.52

 Leyden

0.52

 poichè

0.52

 Shaksp

0.52

 vPvB

0.52

Activations Density 0.044%

mentions of locations and features related to physical spaces

No Known Activations