INDEX

Explanations

patterns or comments that indicate code structure or expectations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 vitamins

-0.53

phazard

-0.53

Vit

-0.49

 Morpho

-0.49

 витами

-0.48

LookAnd

-0.48

 Roskov

-0.47

PhysRev

-0.46

="{

-0.46

 võimal

-0.45

POSITIVE LOGITS

 NSCoder

0.82

 houſe

0.78

 reaſon

0.73

########.

0.72

 raiſ

0.72

躇

0.71

 myſelf

0.70

enumii

0.68

Erstellt

0.68

 ModelExpression

0.68

Activations Density 0.038%

patterns or comments that indicate code structure or expectations

No Comments

No Known Activations