INDEX

Explanations

code comments and documentation structures

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

Text descriptions or documentation

np_acts-logits-general · gemini-2.0-flash

describing functionality or purpose

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ChildScrollView

-0.65

onViewCreated

-0.59

UnusedPrivate

-0.59

tagHelper

-0.58

HtmlAttribute

-0.56

 GenerationType

-0.52

 hitting

-0.52

copyWith

-0.51

 kaynağından

-0.49

lapsingToolbar

-0.49

POSITIVE LOGITS

description

0.75

Provides

0.72

 This

0.70

Description

0.69

 Provides

0.68

 bedoeld

0.68

 provides

0.67

 предназна

0.65

This

0.65

 description

0.65

Activations Density 0.429%

code comments and documentation structures

Text descriptions or documentation

describing functionality or purpose

No Comments

No Known Activations