INDEX

Explanations

patterns or structures in programming or markup languages

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

Code snippets with uncommon terms

np_acts-logits-general · gemini-2.0-flash

computer programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

-0.64

 Wednesday

-0.59

III

-0.54

 third

-0.51

Wednesday

-0.50

 dritten

-0.48

 الثالث

-0.48

 estekak

-0.47

Хьажоргаш

-0.47

iii

-0.47

POSITIVE LOGITS

#+#

0.82

 AssemblyCulture

0.81

 CreateTagHelper

0.78

 للاسماء

0.77

SourceChecksum

0.74

 GenerationType

0.73

providedIn

0.72

ParallelGroup

0.71

 NavController

0.68

 Paglinawan

0.67

Activations Density 0.049%

patterns or structures in programming or markup languages

Code snippets with uncommon terms

computer programming context

No Comments

No Known Activations