INDEX

Explanations

comment indicators and special symbols used in programming or markup languages

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

<start_of_turn>user

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

⟨

-0.64

 Harz

-0.59

 Kommune

-0.57

 Zwer

-0.57

IBOutlet

-0.55

 Baruch

-0.54

屏

-0.54

allowNull

-0.52

 Seil

-0.52

岳

-0.52

POSITIVE LOGITS

0.72

$_"

0.59

//

0.57

 endforeach

0.54

]),

0.52

 iſt

0.52

),

0.51

0.50

uxxxx

0.50

redients

0.50

Activations Density 0.008%

comment indicators and special symbols used in programming or markup languages

<start_of_turn>user

No Comments

No Known Activations

comment indicators and special symbols used in programming or markup languages

<start_of_turn>user

No Comments

No Known Activations