INDEX

Explanations

sequences of numerical values or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

ories

-0.57

dé

-0.56

州市

-0.55

 further

-0.54

 SIMBAD

-0.54

Decrypt

-0.52

дз

-0.49

IVOS

-0.49

rillos

-0.49

fle

-0.48

POSITIVE LOGITS

 autorytatywna

0.77

存于互联网档案馆

0.75

DotNetBar

0.73

AddTagHelper

0.71

GraphicsUnit

0.71

</thead>

0.70

tagHelperRunner

0.69

InjectAttribute

0.69

 ***!

0.68

ValueStyle

0.67

Activations Density 0.056%

sequences of numerical values or measurements

No Comments

No Known Activations