INDEX

Explanations

numerical data and values related to experimental results or observations

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

figure references

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 queſta

-0.75

 utafitiHapana

-0.66

 wireType

-0.63

InitVars

-0.61

encodeWith

-0.60

 Bioaccumulative

-0.60

 resourceCulture

-0.60

存于互联网档案馆

-0.59

bootstrapcdn

-0.59

 getItemId

-0.58

POSITIVE LOGITS

Personendaten

0.33

principalTable

0.30

VersionUID

0.29

期刊论文

0.29

hbase

0.28

]=>

0.27

 AppCompatTheme

0.27

📖

0.27

Fa

0.27

（

0.27

Activations Density 0.037%

numerical data and values related to experimental results or observations

figure references

No Comments

No Known Activations