INDEX

Explanations

mentions of the word "land" in various contexts

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

land followed by sale or use

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

parametrize

-0.49

 veck

-0.49

 Mukherjee

-0.48

#%%

-0.47

<bos>

-0.47

 linkovi

-0.46

kio

-0.45

 teş

-0.45

bewer

-0.44

 Ghosh

-0.44

POSITIVE LOGITS

 land

1.06

 Land

1.03

Land

1.01

 LAND

0.93

land

0.85

 Landry

0.84

 Landis

0.77

 lands

0.76

Lands

0.75

 Lands

0.74

Activations Density 0.016%

mentions of the word "land" in various contexts

land followed by sale or use

No Comments

No Known Activations