INDEX

Explanations

code-related or programming constructs in the text

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

Code snippets (+, template, typename)

np_acts-logits-general · gemini-2.0-flash

technical programming terms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-0.59

 ujednoznacz

-0.56

EndGlobalSection

-0.54

ρών

-0.52

Bug

-0.50

 correctes

-0.49

BagLayout

-0.48

 lautet

-0.47

انظر

-0.47

 jeito

-0.46

POSITIVE LOGITS

 surla

0.69

发表于

0.58

TypedDataSet

0.57

URLException

0.55

IsMutable

0.55

 OnInit

0.53

thâu

0.53

cism

0.51

 NavController

0.50

wpi

0.50

Activations Density 0.105%

code-related or programming constructs in the text

Code snippets (+, template, typename)

technical programming terms

No Comments

No Known Activations