INDEX

Explanations

references to legal cases and rulings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

mathscr

-0.64

agonal

-0.62

Zug

-0.62

 Hwang

-0.61

stral

-0.60

 Hayes

-0.59

ial

-0.58

 musikal

-0.57

 Peker

-0.56

pembe

-0.56

POSITIVE LOGITS

OGND

1.35

 consciences

0.92

ThroughAttribute

0.90

Personensuche

0.89

 Jamieson

0.89

ReusableCell

0.88

ruptedException

0.86

 glycerin

0.86

 Sams

0.85

 Monfieur

0.85

Activations Density 2.166%

references to legal cases and rulings

No Comments

No Known Activations