INDEX

Explanations

programming-related terms and data structure manipulations

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

list slicing and initialization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

spor

-0.36

RTEE

-0.33

Spor

-0.32

trusive

-0.32

</blockquote>

-0.31

ípios

-0.31

ngOnDestroy

-0.30

į

-0.30

undef

-0.29

 отличи

-0.29

POSITIVE LOGITS

Ecotoxicity

0.57

Datuak

0.56

 groupBox

0.56

 houſe

0.56

تقاوى

0.56

AddHtmlAttribute

0.55

 AssemblyTitle

0.55

GEBURTSDATUM

0.55

 informée

0.55

 greateſt

0.55

Activations Density 0.021%

programming-related terms and data structure manipulations

list slicing and initialization

No Comments

No Known Activations