INDEX

Explanations

numbers or expressions related to quantity or values

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

Code, formulas, or technical language

np_acts-logits-general · gemini-2.0-flash

academic and technical acronyms

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

MessageTagHelper

-0.76

adpleegd

-0.63

Ingredienti

-0.61

 trajets

-0.61

utrients

-0.57

MergeFrom

-0.57

utenant

-0.54

wiring

-0.53

cobacterium

-0.53

openConnection

-0.52

POSITIVE LOGITS

msgTypes

0.64

 autorytatywna

0.63

KommentareTeilen

0.54

 NSCoder

0.54

UnsafeEnabled

0.54

ISupport

0.52

告

0.47

固

0.46

CodeAttribute

0.45

出版年

0.45

Activations Density 0.933%

numbers or expressions related to quantity or values

Code, formulas, or technical language

academic and technical acronyms

No Comments

No Known Activations