INDEX

Explanations

patterns and structures in data representations

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

principalColumn

-0.64

 intStringLen

-0.63

keyColumn

-0.61

Jereo

-0.60

 StatelessWidget

-0.60

webElementGuid

-0.57

 ObjectParameter

-0.53

loem

-0.52

BASEPATH

-0.50

rrggbb

-0.49

POSITIVE LOGITS

1.41

nesc

0.65

 Waray

0.65

&_

0.61

ViewFeatures

0.57

setVerticalGroup

0.57

TagHelper

0.56

bete

0.55

RTDA

0.55

FormsModule

0.55

Activations Density 0.105%

patterns and structures in data representations

No Comments

No Known Activations