INDEX

Explanations

expressions of frustration or problems related to understanding concepts and issues

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للمعارف

-0.83

lapsingToolbar

-0.70

httphttps

-0.67

 ComVisible

-0.64

 MainAxisSize

-0.63

Controllo

-0.62

 odkazy

-0.61

 referenties

-0.61

 متعلقه

-0.60

Precalculus

-0.60

POSITIVE LOGITS

 thing

0.99

 goal

0.83

aim

0.77

 reason

0.73

 caveat

0.66

 question

0.66

 hope

0.66

 idea

0.65

 cosa

0.64

 point

0.63

Activations Density 0.512%

expressions of frustration or problems related to understanding concepts and issues

No Comments

No Known Activations