INDEX

Explanations

terms related to academic and research integrity

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

Limitations, aspects, differences, range, alteration, variation

np_acts-logits-general · gemini-2.0-flash

abstract concepts and classifications

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

CppMethod

-0.54

Referencias

-0.45

式

-0.45

 typelib

-0.43

YMMV

-0.42

 aasta

-0.41

település

-0.40

jarse

-0.39

cidae

-0.39

Ox

-0.39

POSITIVE LOGITS

ValueGeneration

0.81

 pinulongan

0.77

BeginContext

0.72

 onCancelled

0.72

onAttach

0.71

 fieldNum

0.68

AddHtmlAttribute

0.68

extAlignment

0.66

 мәкал

0.66

 kasarigan

0.65

Activations Density 1.201%

terms related to academic and research integrity

Limitations, aspects, differences, range, alteration, variation

abstract concepts and classifications

No Comments

No Known Activations