INDEX

Explanations

references to official regulations or terms related to data processing

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

important factor

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

脚注の使い方

-0.94

 erſt

-0.93

 ddelwed

-0.91

expandindo

-0.89

ſelben

-0.88

<unused41>

-0.86

<unused43>

-0.86

<unused28>

-0.86

<pad>

-0.86

[@BOS@]

-0.86

POSITIVE LOGITS

KURZBESCHREIBUNG

0.24

=="

0.24

ab

0.22

ab

0.22

*)

0.22

 Suppl

0.22

mod

0.22

ac

0.21

mod

0.21

US

0.21

Activations Density 0.160%

references to official regulations or terms related to data processing

important factor

No Comments

No Known Activations