INDEX

Explanations

mentions of "activities" and related terms

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

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

<bos>

-0.61

 plegable

-0.50

 garansi

-0.48

 originais

-0.47

 ecológico

-0.46

 importado

-0.45

 Cientí

-0.44

 nine

-0.44

 mijne

-0.44

 personalizadas

-0.44

POSITIVE LOGITS

 activity

1.24

 Activity

1.20

Activity

1.12

 Activities

1.08

 activities

1.08

activity

1.05

 ACTIVITY

1.04

Activities

1.02

activities

0.99

 getActivity

0.98

Activations Density 0.023%

mentions of "activities" and related terms

activities

No Comments

No Known Activations