INDEX

Explanations

references to specific films and their characteristics

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

pop culture, music, and film

np_acts-logits-general · gemini-2.0-flash

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

 Federer

-0.58

 Hinata

-0.52

idopsis

-0.52

 camry

-0.50

 subtilis

-0.50

 Strava

-0.49

phosa

-0.48

garmin

-0.48

 Rashford

-0.48

 Nadal

-0.47

POSITIVE LOGITS

 burlesque

0.51

 cabaret

0.50

 eccentric

0.49

 drag

0.49

 Marilyn

0.48

 flamboyant

0.46

 kits

0.45

drag

0.44

 Lichten

0.44

 glam

0.42

Activations Density 0.195%

references to specific films and their characteristics

pop culture, music, and film

No Comments

No Known Activations