INDEX

Explanations

numerical data or sequences

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NameInMap

-0.92

 Bourgoin

-0.79

/***/

-0.76

IBarButtonItem

-0.74

DockStyle

-0.74

AndEndTag

-0.73

|')

-0.70

 BorderSide

-0.70

 AssemblyTitle

-0.68

TagMode

-0.68

POSITIVE LOGITS

enchymal

0.51

 surla

0.51

컸

0.49

Vin

0.48

 kindly

0.45

ريع

0.45

 overras

0.43

 virš

0.42

BooleanField

0.42

 dře

0.42

Activations Density 0.229%

numerical data or sequences

No Comments

No Known Activations