INDEX

Explanations

named entities or specific references related to locations and individuals

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

Code, math, or file-related tokens

np_acts-logits-general · gemini-2.0-flash

Kyutama

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

AddTagHelper

-0.68

 intStringLen

-0.56

 metus

-0.44

beginPath

-0.43

 ویکی‌پدیای

-0.43

⎨

-0.43

RTLI

-0.42

ģ

-0.41

LITERAL

-0.41

 Christo

-0.41

POSITIVE LOGITS

omitempty

0.50

KommentareTeilen

0.42

AnimationsModule

0.41

expandindo

0.40

AxisAlignment

0.39

 <<<<<<<<<<<<<<

0.39

 שוליים

0.38

[]:

0.36

cshtml

0.35

adaptiveStyles

0.35

Activations Density 0.879%

named entities or specific references related to locations and individuals

Code, math, or file-related tokens

Kyutama

No Comments

No Known Activations