INDEX

Explanations

proper nouns, specifically names of individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

TagHelper

-0.60

Története

-0.56

AnchorTagHelper

-0.56

ScopeManager

-0.55

WebMethod

-0.53

LabelTagHelper

-0.53

RenderAtEndOf

-0.53

Ndr

-0.52

AccessorTable

-0.52

DockStyle

-0.52

POSITIVE LOGITS

 AssemblyVersion

0.62

Autoritní

0.57

 مواليد

0.50

httphttps

0.49

ionales

0.48

 個人

0.47

 Driven

0.46

 Gerr

0.46

__":

0.44

Enllaços

0.44

Activations Density 0.046%

proper nouns, specifically names of individuals or entities

No Comments

No Known Activations