INDEX

Explanations

information related to classifications, attributes, and properties of various entities

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

Category:value pairs

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

ftagPool

-0.98

exitRule

-0.83

RegressionTest

-0.81

tagHelperRunner

-0.69

 imagui

-0.68

ſſung

-0.66

 مرئيه

-0.66

 laſſen

-0.65

<unused79>

-0.65

[@BOS@]

-0.65

POSITIVE LOGITS

Name

0.36

Length

0.35

0.33

 Type

0.33

name

0.32

es

0.31

ID

0.31

britanni

0.31

目的

0.30

Activations Density 0.093%

information related to classifications, attributes, and properties of various entities

Category:value pairs

No Comments

No Known Activations