INDEX

Explanations

references to programming libraries and dependencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

MemoryWarning

-1.22

 kasarigan

-1.21

#+#

-1.05

__(/*!

-1.04

ReusableCell

-1.04

AnchorStyles

-0.98

CppMethod

-0.95

extAlignment

-0.94

 CreateTagHelper

-0.87

PointerException

-0.87

POSITIVE LOGITS

Rüyada

0.52

נון

0.41

aman

0.41

 ImGui

0.40

 препратки

0.39

alam

0.38

multer

0.37

正

0.37

ئه

0.37

den

0.36

Activations Density 0.352%

references to programming libraries and dependencies

No Comments

No Known Activations