INDEX

Explanations

references to the term "driver."

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

driver and vehicle contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 Neuf

-0.55

Enllaços

-0.52

 Pease

-0.51

addGap

-0.51

Extent

-0.50

 Holt

-0.47

 Schmel

-0.47

divide

-0.47

arrête

-0.46

 Holtz

-0.46

POSITIVE LOGITS

 Driver

0.99

 Drivers

0.84

Driver

0.84

 DRIVER

0.81

 driver

0.79

driver

0.77

Drivers

0.77

 Treiber

0.74

 Rider

0.73

ruiter

0.72

Activations Density 0.009%

references to the term "driver."

driver and vehicle contexts

No Comments

No Known Activations