INDEX

Explanations

phrases related to inspections or evaluations

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

Sentences containing "is" or variations

np_acts-logits-general · gemini-2.0-flash

acting like, five level

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

tivism

-0.60

 Sebab

-0.59

 שוליים

-0.56

новништво

-0.54

 krav

-0.52

providedIn

-0.52

 виправивши

-0.51

 Fate

-0.51

Objetivos

-0.51

址

-0.50

POSITIVE LOGITS

IsContent

0.55

Rudy

0.47

Addendum

0.46

 recientemente

0.46

 BorderRadius

0.46

Lew

0.45

 AssemblyProduct

0.45

ēd

0.44

twimg

0.44

::__

0.43

Activations Density 0.059%

phrases related to inspections or evaluations

Sentences containing "is" or variations

acting like, five level

No Comments

No Known Activations