INDEX

Explanations

keywords and expressions related to programming and server management

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

Code, URLs, and filenames

np_acts-logits-general · gemini-2.0-flash

legal entities and web addresses

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

########.

-0.45

ChildScrollView

-0.45

bootstrapcdn

-0.44

dicionado

-0.41

AutoScaleMode

-0.40

gatsby

-0.40

jacent

-0.40

 permiso

-0.39

findpost

-0.39

TypedDataSet

-0.38

POSITIVE LOGITS

ternut

0.50

AccessorTable

0.41

TSH

0.39



0.38

CPL

0.36

uffff

0.36

__()

0.36

Couch

0.36

曖昧さ回避

0.36

ptonshire

0.36

Activations Density 0.408%

keywords and expressions related to programming and server management

Code, URLs, and filenames

legal entities and web addresses

No Comments

No Known Activations