INDEX

Explanations

elements related to data structures and programming syntax

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

Code snippets and identifiers

np_acts-logits-general · gemini-2.0-flash

code tokens and punctuation

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

 alike

-0.76

DoubleQuotes

-0.69

первых

-0.68

━━━

-0.65

Portale

-0.64

 Theſe

-0.63

 PagesJaunes

-0.62

 समीक्षक

-0.61

 erop

-0.60

ViewChild

-0.58

POSITIVE LOGITS

EndInit

0.81

and

0.72

0.67

GenerationType

0.60

 Paglinawan

0.55

ValueStyle

0.54

이고

0.53

reportWebVitals

0.45

 Roskov

0.45

Activations Density 0.647%

elements related to data structures and programming syntax

Code snippets and identifiers

code tokens and punctuation

No Comments

No Known Activations