INDEX

Explanations

terms related to career advancement and rewards

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

AutoresizingMask

-0.66

tear

-0.50

 فريبيس

-0.47

nee

-0.45

 köl

-0.44

diğinde

-0.44

pM

-0.44

kurat

-0.44

 user

-0.43

Sonntag

-0.43

POSITIVE LOGITS

 rewarded

0.93

 reward

0.92

 rewards

0.86

reward

0.75

rewards

0.74

 Rewards

0.69

ViewImports

0.69

findpost

0.68

 Reward

0.67

Reward

0.67

Activations Density 0.566%

terms related to career advancement and rewards

No Comments

No Known Activations