INDEX

Explanations

quantifiable metrics or measurements in a context

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

indices, matrices, equations

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

principalTable

-0.63

 NSCoder

-0.62

awaiter

-0.61

 виправивши

-0.60

XtraReports

-0.59

 HasFactory

-0.57

 autorytatywna

-0.57

PhysRev

-0.57

 psycopg

-0.57

andExpect

-0.56

POSITIVE LOGITS

 deines

0.33

jsonwebtoken

0.28

 będ

0.28

 multip

0.28

 brukar

0.27

 μα

0.27

 Zahl

0.27

 daerah

0.26

ajevo

0.26

'";

0.25

Activations Density 0.004%

quantifiable metrics or measurements in a context

indices, matrices, equations

No Comments

No Known Activations