INDEX

Explanations

phrases related to interactions or actions involving clicking or expanding content

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

"Click" followed by an action

np_acts-logits-general · gemini-2.0-flash

click to enlarge or here

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 dépôt

-0.46

Eleven

-0.45

erste

-0.44

стка

-0.42

 pyplot

-0.42

 wireType

-0.42

idase

-0.41

styleType

-0.40

 Werth

-0.39

 simplifié

-0.38

POSITIVE LOGITS

BagConstraints

0.74

 Expand

0.72

 expansion

0.72

__":

0.69

 expand

0.68

ngdoc

0.68

AddTagHelper

0.67

VersionUID

0.67

SpringBootTest

0.67

 Expansion

0.67

Activations Density 0.037%

phrases related to interactions or actions involving clicking or expanding content

"Click" followed by an action

click to enlarge or here

No Comments

No Known Activations