INDEX

Explanations

references to power, particularly in contexts related to energy, utilities, and control systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SpringBootTest

-0.97

 ControllerBase

-0.88

 للاسماء

-0.85

principalTable

-0.83

 AspNetCore

-0.80

IUrlHelper

-0.78

IsMutable

-0.76

 dieß

-0.76

Personensuche

-0.76

Rüyada

-0.75

POSITIVE LOGITS

houses

0.70

house

0.62

 Powers

0.57

 Power

0.57

 powers

0.56

 POWER

0.55

 power

0.54

powers

0.53

Powers

0.53

POWER

0.51

Activations Density 0.083%

references to power, particularly in contexts related to energy, utilities, and control systems

No Comments

No Known Activations