INDEX

Explanations

references to levers and their associated mechanisms or actions

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

lever

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

 Kond

-0.48

 Cosmos

-0.45

 Kathleen

-0.45

 Blackout

-0.44

 quarantined

-0.44

 Whitfield

-0.44

 Prato

-0.44

 Darmstadt

-0.43

 Kong

-0.43

 Kondo

-0.43

POSITIVE LOGITS

 lever

1.98

 Lever

1.88

Lever

1.86

lever

1.73

 levers

1.52

 levier

1.34

 palanca

1.34

 leveraged

1.26

 leverage

1.21

 Leverage

1.19

Activations Density 0.005%

references to levers and their associated mechanisms or actions

lever

No Comments

No Known Activations

references to levers and their associated mechanisms or actions

lever

No Comments

No Known Activations