INDEX

Explanations

references to biological objects, processes, or entities

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

Likely misspelled or truncated words/tokens

np_acts-logits-general · gemini-2.0-flash

scientific and academic references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 appris

-0.24

ativität

-0.24

 descans

-0.22

</strong>

-0.21

 Capitán

-0.21

 matin

-0.20

rzez

-0.20

 gente

-0.20

 internos

-0.19

 nocturno

-0.19

POSITIVE LOGITS

Personendaten

0.79

featureID

0.79

IUrlHelper

0.76



0.74

 Administrativna

0.73

 препратки

0.72

rungsseite

0.70



0.69

出版年

0.69

 ویکی‌پدیا

0.69

Activations Density 0.801%

references to biological objects, processes, or entities

Likely misspelled or truncated words/tokens

scientific and academic references

No Comments

No Known Activations

references to biological objects, processes, or entities

Likely misspelled or truncated words/tokens

scientific and academic references

No Comments

No Known Activations