INDEX

Explanations

references to giving or trying something, particularly in a context of effort or exploration

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

After the tokens "a" or "one"

np_acts-logits-general · gemini-2.0-flash

articles followed by actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

+#+#

-0.56

DialogInterface

-0.55

 Riproduzione

-0.55

 soie

-0.53

Vidite

-0.53

 Rapport

-0.51

 مرئيه

-0.50

occuper

-0.50

 createState

-0.50

 sonriendo

-0.49

POSITIVE LOGITS

 shot

1.65

shot

1.36

go

1.29

 crack

1.28

 Shot

1.27

 shots

1.26

 SHOT

1.21

Shot

1.17

try

1.16

SHOT

1.14

Activations Density 0.191%

references to giving or trying something, particularly in a context of effort or exploration

After the tokens "a" or "one"

articles followed by actions

No Comments

No Known Activations