INDEX

Explanations

references to legal processes and arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

setTypeface

-0.66

endphp

-0.58

OrNil

-0.53

ceği

-0.51

 برانيه

-0.51

 demografica

-0.47

cektir

-0.47

edere

-0.47

bootstrapcdn

-0.47

roides

-0.46

POSITIVE LOGITS

 saying

2.62

saying

2.15

 stating

2.14

 noting

2.00

 citing

1.86

Saying

1.85

 Saying

1.82

 diciendo

1.67

 sayin

1.62

 pointing

1.59

Activations Density 0.402%

references to legal processes and arguments

No Comments

No Known Activations