INDEX

Explanations

legal case citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 itſelf

-0.81

存于互联网档案馆

-0.76

 poffible

-0.71

ſelves

-0.70

 houſe

-0.69

 ſche

-0.69

 raiſ

-0.68

 myſelf

-0.68

 rospy

-0.67

 neceſſ

-0.66

POSITIVE LOGITS

0.67

volo

0.59

ruck

0.57

VS

0.56

rasil

0.56

poons

0.56

adin

0.55

 AssemblyCompany

0.55

Kariera

0.54

Trama

0.54

Activations Density 0.183%

legal case citations

No Comments

No Known Activations