INDEX

Explanations

references to specific technical objects and concepts, particularly within coding and scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 مرئيه

-0.54

MessageOf

-0.53

ToolStripButton

-0.50

 وصلة

-0.50

μφωνα

-0.49

bigsqcup

-0.48

sû

-0.47

 Prefeitura

-0.47

intenant

-0.47

orsche

-0.47

POSITIVE LOGITS

 pinulongan

0.74

ILayout

0.72

 twin

0.71

IsPostBack

0.68

 EventArgs

0.67

Portály

0.67

enumi

0.65

makeText

0.64

IContainer

0.63

 springs

0.63

Activations Density 2.134%

references to specific technical objects and concepts, particularly within coding and scientific contexts

No Comments

No Known Activations