INDEX

Explanations

superlative descriptors related to quality and significance

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

best, premier, most vibrant

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

ThroughAttribute

-0.54

ValueStyle

-0.49

Amicalement

-0.46

EndInit

-0.46

InitVars

-0.45

 препратки

-0.44

 незавершена

-0.44

intios

-0.43

сылкі

-0.42

الدراسه

-0.41

POSITIVE LOGITS

 vectorielles

0.43

 mayor

0.37

 rivers

0.34

 soil

0.34

arikat

0.34

 Icelandic

0.34

 civic

0.33

 local

0.33

yntaxException

0.33

 HasFactory

0.32

Activations Density 0.067%

superlative descriptors related to quality and significance

best, premier, most vibrant

No Comments

No Known Activations