INDEX

Explanations

the concept of being "behind" or underlying factors influencing various situations

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

behind this

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

 fisk

-0.39

sspiel

-0.36

onation

-0.36

发表于

-0.36

angliski

-0.35

None

-0.35

Scale

-0.34

 reag

-0.34

EXPORT

-0.34

</table>

-0.33

POSITIVE LOGITS

 BEHIND

1.66

 Behind

1.63

Behind

1.60

 behind

1.59

behind

1.55

 detrás

1.27

 bakom

1.27

 derrière

1.26

Hinter

1.24

 achter

1.17

Activations Density 0.011%

the concept of being "behind" or underlying factors influencing various situations

behind this

No Comments

No Known Activations