INDEX

Explanations

phrases related to authority, control, and the influence exerted by powerful figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

MigrationBuilder

-0.68

SharedDtor

-0.67

 NSCoder

-0.62

Havolalar

-0.61

 ExecuteAsync

-0.60

 bezeichneter

-0.60

 ProtoMessage

-0.59

 الحره

-0.58

FunctionFlags

-0.58

complexContent

-0.58

POSITIVE LOGITS

 willingly

0.79

 willingness

0.75

 voluntarily

0.74

 willing

0.72

 reluctant

0.70

 Willing

0.68

 freiw

0.67

 motivated

0.67

 motivation

0.64

 incentive

0.63

Activations Density 0.374%

phrases related to authority, control, and the influence exerted by powerful figures

No Comments

No Known Activations