INDEX

Explanations

numerical data, references to subsections, and elements indicating structure within a document

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

section followed by list or text

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

ंदीखरीदारी

-0.43

%");

-0.39

protoimpl

-0.39

SequentialGroup

-0.38

DoubleQuotes

-0.37

GOTREF

-0.37

_));

-0.36

TagMode

-0.35

]");

-0.34

Handlung

-0.33

POSITIVE LOGITS

Rhestr

0.48

 TextAlign

0.46

bleib

0.45

 Wartawan

0.45

 مُعرِّف

0.44

covo

0.43

 Wicidata

0.43

 otomatig

0.42

 continúas

0.41

cogn

0.41

Activations Density 0.014%

numerical data, references to subsections, and elements indicating structure within a document

section followed by list or text

No Comments

No Known Activations