INDEX

Explanations

occurrences of the word "result" or its variations

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

 تانيه

-0.90

SharedCtor

-0.80

reveal

-0.68

 Gabe

-0.67

 presidencial

-0.65

 Haddad

-0.65

 Pyrr

-0.65

 Mald

-0.64

 Zand

-0.64

ponses

-0.64

POSITIVE LOGITS

الإنجليزية

0.78

المكان

0.59

 role

0.58

parsedMessage

0.57

Према

0.56

 noDo

0.55

 factors

0.54

伴

0.54

 arising

0.54

urlar

0.54

Activations Density 0.022%

occurrences of the word "result" or its variations

No Known Activations