INDEX

Explanations

specific references to geographic locations and their associated data in various contexts

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

Code, module, or install-related text

np_acts-logits-general · gemini-2.0-flash

Twp, List, Message, install, tao

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

AndEndTag

-0.86

featureID

-0.64

GEBURTSDATUM

-0.64

 gainera

-0.58

 ModelExpression

-0.54

explique

-0.49

données

-0.49

FieldBuilder

-0.47

 CreateTagHelper

-0.46

FieldDescriptor

-0.46

POSITIVE LOGITS

 tfsi

0.62

 تضيفلها

0.62

 BorderSide

0.58

躇

0.58

?"

0.57

KommentareTeilen

0.57

 telt

0.56

 tdci

0.56

 hentai

0.56

ècie

0.56

Activations Density 0.120%

specific references to geographic locations and their associated data in various contexts

Code, module, or install-related text

Twp, List, Message, install, tao

No Comments

No Known Activations