INDEX

Explanations

placeholders or structural elements in coding or markup

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

Code-related syntax ( {, }, (,)

np_acts-logits-general · gemini-2.0-flash

code delimiters and programming terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

照

-0.53

issus

-0.49

setState

-0.47

gon

-0.47

labelControl

-0.47

 issue

-0.46

대로

-0.46

酌

-0.45

 with

-0.45

actionMode

-0.45

POSITIVE LOGITS

 виправивши

0.88

OGND

0.87

StoryboardSegue

0.81

findpost

0.77

EndGlobalSection

0.76

 surla

0.74

expandindo

0.73

WebVitals

0.72

 Chwiliwch

0.71

 beginnetje

0.69

Activations Density 0.072%

placeholders or structural elements in coding or markup

Code-related syntax ( {, }, (,)

code delimiters and programming terms

No Comments

No Known Activations