INDEX

Explanations

references to legal and governmental entities, roles, or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 חיצוניים

-0.60

AddTagHelper

-0.60

InputBorder

-0.52

ViewImports

-0.51

]-->

-0.51

ScopeManager

-0.50

 AssemblyCulture

-0.49

Datuak

-0.48

もと

-0.47

 onOptions

-0.47

POSITIVE LOGITS

 către

0.78

ⓧ

0.68

 soins

0.65

 Walkover

0.62

 blancas

0.60

 memoized

0.59

 disponibilités

0.59

ellschaft

0.58

Dearest

0.58

 bulunabilir

0.58

Activations Density 0.685%

references to legal and governmental entities, roles, or processes

No Comments

No Known Activations