INDEX

Explanations

elements related to data processing and subscriptions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

data bus, memory, logs, code

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

Negative Logits

 appelez

-0.49

原始内容存档于

-0.46

iet

-0.39

 Pablo

-0.39

cleo

-0.38

 protoimpl

-0.37

Jon

-0.35

pol

-0.35

IBAction

-0.35

Ban

-0.35

POSITIVE LOGITS

$_"

0.46

 Infór

0.46

 enfans

0.46

-------

0.45

istoitu

0.45

 desmotivaciones

0.45

 themſelves

0.45

 étoient

0.44

ťaž

0.44

BeginInit

0.44

Activations Density 0.112%

elements related to data processing and subscriptions

data bus, memory, logs, code

No Known Activations