INDEX

Explanations

various programming language constructs and commands related to data manipulation and structure

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

Code snippets with terms like "options", "data", and "state"

np_acts-logits-general · gemini-2.0-flash

code block structures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

FTFY

-0.53

</h2>

-0.52

RetentionPolicy

-0.49

setVerticalGroup

-0.48

OOTDTY

-0.46

נוּ

-0.46

rtz

-0.46

 BoxFit

-0.45

DOCTYPE

-0.45

Badges

-0.43

POSITIVE LOGITS

 "..\..\..\

0.66

 "..\..\

0.66

исленность

0.64

SequentialGroup

0.62

 Chwiliwch

0.62

 initComponents

0.62

 '\\;'

0.55

NameInMap

0.55

็จ

0.54

 iprot

0.54

Activations Density 0.223%

various programming language constructs and commands related to data manipulation and structure

Code snippets with terms like "options", "data", and "state"

code block structures

No Comments

No Known Activations