INDEX

Explanations

phrases related to assessments or evaluations of objects or experiences

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

List continuation with "etc" or similar abbreviations

np_acts-logits-general · gemini-2.0-flash

lists and examples

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

openqa

-0.78

 propOrder

-0.77

stateProvider

-0.71

 typelib

-0.69

 مرئيه

-0.68

 ivelany

-0.67

řevě

-0.66

 يتيمه

-0.66

 CreateTagHelper

-0.65

 BoxFit

-0.65

POSITIVE LOGITS

or

0.63

也可

0.59

也可以

0.52

 oder

0.50

 especially

0.50

 geeignet

0.49

Especially

0.48

especially

0.47

或

0.47

也能

0.47

Activations Density 0.331%

phrases related to assessments or evaluations of objects or experiences

List continuation with "etc" or similar abbreviations

lists and examples

No Comments

No Known Activations