INDEX

Explanations

technical terminology and definitions related to specific processes or measurements

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

listing specific data

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

+#+#

-0.59

endphp

-0.53

useState

-0.48

PerformLayout

-0.48

LabelTagHelper

-0.47

 useState

-0.47

+#+

-0.45

XmlAccessType

-0.43

]")]

-0.43

IUrlHelper

-0.43

POSITIVE LOGITS

Autoritní

0.65

 nahilalakip

0.60

rungsseite

0.56

AISSEE

0.51

AddTagHelper

0.48

isContained

0.45

RTLI

0.44

 Италијани

0.43

MEMORANDUM

0.43

 AssemblyCulture

0.42

Activations Density 0.194%

technical terminology and definitions related to specific processes or measurements

listing specific data

No Comments

No Known Activations