INDEX

Explanations

references to skills and competencies

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

"])){

-0.75

Personensuche

-0.74

"]];

-0.74

 portatil

-0.73

\}\\

-0.72

tze

-0.70

?«

-0.69

»-

-0.68

 Fontaine

-0.67

?");

-0.67

POSITIVE LOGITS

 Skills

1.13

skills

1.07

 skills

1.05

 Skill

1.02

 SKILLS

1.00

SKILL

0.94

 skill

0.94

Skills

0.92

msgSender

0.88

skill

0.82

Activations Density 0.010%

references to skills and competencies

No Comments

No Known Activations