INDEX

Explanations

question marks denoting inquiries or uncertainties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RegressionTest

-0.88

AddTagHelper

-0.74

 betweenstory

-0.67

tagHelperRunner

-0.65

 kasarigan

-0.64

TypedDataSet

-0.63

BufferException

-0.59

 PeEnEo

-0.59

 المعيارى

-0.56

StructEnd

-0.53

POSITIVE LOGITS

<u>

0.39

SBATCH

0.39

0.37

 propOrder

0.35

říve

0.34

чника

0.34

 telefónica

0.34

Enigma

0.33

IActionResult

0.33

 mother

0.32

Activations Density 0.369%

question marks denoting inquiries or uncertainties

No Comments

No Known Activations