INDEX

Explanations

phrases that indicate direction or a path

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

lead verb indicating direction

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

 comigo

-0.50

ValueStyle

-0.47

 ciudadana

-0.47

latego

-0.45

 zijne

-0.44

 pesanan

-0.43

 työn

-0.42

 previsão

-0.42

 toekomst

-0.41

zanas

-0.41

POSITIVE LOGITS

 leading

0.77

 lead

0.75

 leads

0.65

leading

0.64

 Lead

0.64

 Leading

0.63

lead

0.60

Leading

0.59

 Leads

0.59

led

0.58

Activations Density 0.012%

phrases that indicate direction or a path

lead verb indicating direction

No Comments

No Known Activations