INDEX

Explanations

syntax structures and expressions common in programming code

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

Code snippets/fragments

np_acts-logits-general · gemini-2.0-flash

technical content and code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

medriver

-0.55

styleType

-0.53

VersionUID

-0.52

MessageOf

-0.50

ReusableCell

-0.49

 onCreateView

-0.47

posedge

-0.47

endpush

-0.47

adaptiveStyles

-0.46

 ActivatedRoute

-0.46

POSITIVE LOGITS

期刊论文

0.42

SequentialGroup

0.37

NamedQueries

0.35

ARIUS

0.34

pya

0.34

retanto

0.33

ांकि

0.33

{#

0.32

ListModule

0.32

ाहरण

0.32

Activations Density 0.068%

syntax structures and expressions common in programming code

Code snippets/fragments

technical content and code

No Comments

No Known Activations