INDEX

Explanations

syntactic markers and elements related to programming or scripting languages

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

Code, versions, or programming-related text

np_acts-logits-general · gemini-2.0-flash

code and technical writing

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

 know

-1.25

know

-1.06

 Know

-0.97

Know

-0.97

 knows

-0.93

 KNOW

-0.80

KNOW

-0.74

 known

-0.73

 γνω

-0.71

你知道

-0.68

POSITIVE LOGITS

Personensuche

0.69

AutoresizingMask

0.64

queryInterface

0.63

 typelib

0.63

CodedInputStream

0.59

principalTable

0.58

ThroughAttribute

0.57

StructEnd

0.55

PerformLayout

0.54

reportWebVitals

0.52

Activations Density 0.493%

syntactic markers and elements related to programming or scripting languages

Code, versions, or programming-related text

code and technical writing

No Comments

No Known Activations