INDEX

Explanations

key structural components or outlines in written guidance or documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

gure

-0.54

QUENCE

-0.49

énéral

-0.48

enna

-0.48

Tri

-0.48

runt

-0.47

addGap

-0.47

 đoạn

-0.46

нке

-0.45

pean

-0.44

POSITIVE LOGITS

:✨

0.87

/**

0.77

 للاسماء

0.76

 resourceCulture

0.76

AlterField

0.75

 estekak

0.74

ModelSerializer

0.74

__":

0.74

TagMode

0.72

rungsseite

0.71

Activations Density 0.102%

key structural components or outlines in written guidance or documentation

No Comments

No Known Activations