INDEX

Explanations

references to specific issues or complexities in scientific studies or analyses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

kloped

-0.60

addGap

-0.57

новништво

-0.53

ViewFeatures

-0.53

нциклопедия

-0.51

scriptcase

-0.50

<eos>

-0.50

 desselben

-0.47

 duke

-0.45

PhysRev

-0.45

POSITIVE LOGITS

 الحره

0.90

 ModelExpression

0.78

ChildScrollView

0.76

IntoConstraints

0.74

]--;

0.72

EDEFAULT

0.71

RectangleBorder

0.70

رشف

0.68

ImageContext

0.68

CloseOperation

0.68

Activations Density 1.704%

references to specific issues or complexities in scientific studies or analyses

No Comments

No Known Activations