INDEX

Explanations

instances of code or markup structure with nested elements

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

HTML tags, attributes, and code snippets

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

jsonwebtoken

-0.54

TagMode

-0.53

ToAction

-0.44

ttino

-0.44

LayoutConstraint

-0.43

disposing

-0.43

WriteLiteral

-0.42

 BaseActivity

-0.42

 INTERESAR

-0.42

QRect

-0.42

POSITIVE LOGITS

EFIAPI

0.54

المكان

0.46

Jereo

0.45

protoimpl

0.45

 lenker

0.44

+#+

0.43

complexContent

0.42

="@+

0.42

MockBean

0.42

 Grimal

0.41

Activations Density 0.030%

instances of code or markup structure with nested elements

HTML tags, attributes, and code snippets

No Comments

No Known Activations