INDEX

Explanations

phrases related to occurrences or events

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

Questions about events occurring

np_acts-logits-general · gemini-2.0-flash

events or occurrences

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

wiſe

-0.49

ewe

-0.49

}{*}{

-0.48

SourceChecksum

-0.46

Denise

-0.45

CFA

-0.43

 stöd

-0.43

eſ

-0.43

 äls

-0.42

 föres

-0.42

POSITIVE LOGITS

happen

1.28

 happen

1.20

 happened

1.17

happened

1.16

 Happened

1.16

 happens

1.16

 happening

1.15

happens

1.15

 Happen

1.13

 Happening

1.09

Activations Density 0.112%

phrases related to occurrences or events

Questions about events occurring

events or occurrences

No Comments

No Known Activations