INDEX

Explanations

actions involving movement or manual tasks

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

actions and activities

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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



-0.62

 MainAxisSize

-0.61

 Paglinawan

-0.61

principalTable

-0.60

 defaultstate

-0.60

 ویکی‌پدیا

-0.60

recated

-0.59

HtmlAttribute

-0.58

Organisateur

-0.57

GTCX

-0.57

POSITIVE LOGITS

 trying

0.44

 accident

0.44

 accidentally

0.38

たまたま

0.38

accident

0.36

 Accident

0.36

Accident

0.36

 talking

0.35

trying

0.34

 navegando

0.33

Activations Density 0.085%

actions involving movement or manual tasks

actions and activities

No Comments

No Known Activations