INDEX

Explanations

architectural features and specifications of properties

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

specific words followed by descriptions

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Audiodateien

-0.63

 utafitiHapana

-0.63

 dAtA

-0.61

 emot

-0.60

ophageal

-0.54

spice

-0.52

ActionButton

-0.52

Sparks

-0.52

 Spas

-0.52

OfWork

-0.52

POSITIVE LOGITS

 beds

0.56

 dormitorios

0.53

Tikang

0.52

writeFieldEnd

0.52

apkamer

0.51

Beds

0.50

 AssemblyCompany

0.49

RuleContext

0.48

 TextAppearance

0.48

telsen

0.48

Activations Density 0.003%

architectural features and specifications of properties

specific words followed by descriptions

No Comments

No Known Activations