INDEX

Explanations

punctuations and symbols used in complex structures or programming languages

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

mathematical and programming terms

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

 Infórmanos

-0.46

pe

-0.44

GEBURTS

-0.42

ymal

-0.42

ersburg

-0.41

 queue

-0.38

__(/*!

-0.38

cim

-0.37

 ComVisible

-0.36

HOS

-0.36

POSITIVE LOGITS

MigrationBuilder

0.58

PropertyChanging

0.55

providedIn

0.52

Erreferentziak

0.50

Personendaten

0.47

DebuggerStep

0.46

 esternos

0.45

 estekak

0.44

 وتسجيلات

0.41

CopyWith

0.40

Activations Density 0.258%

punctuations and symbols used in complex structures or programming languages

mathematical and programming terms

No Comments

No Known Activations