INDEX

Explanations

references to box dimensions and attributes in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

withstanding

-0.92

 pleaſure

-0.84

ModelAdmin

-0.82

aarrggbb

-0.81

PerformLayout

-0.79

*/),

-0.79

DSA

-0.77

 Ciri

-0.75

rslt

-0.75

PRET

-0.74

POSITIVE LOGITS

Box

2.06

BOX

2.06

box

2.06

 boxes

1.97

box

1.89

BOX

1.86

 Boxes

1.80

Box

1.79

boxes

1.67

Boxes

1.51

Activations Density 0.052%

references to box dimensions and attributes in code

No Comments

No Known Activations