INDEX

Explanations

mentions of protected attributes in class definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

########.

-0.75

ícil

-0.69

دانشنامهٔ

-0.65

 antigen

-0.61

InputBorder

-0.60

 NgModule

-0.58

ButtonStyle

-0.58

 Antigen

-0.58

lgari

-0.58

 Wheels

-0.58

POSITIVE LOGITS

MigrationBuilder

0.69

SequentialGroup

0.64

+#+#

0.57

0.51

 propOrder

0.50

optionalTypeArgs

0.49

 tarko

0.48

 "..\..\

0.48

etc

0.46

consulté

0.46

Activations Density 0.142%

mentions of protected attributes in class definitions

No Comments

No Known Activations