INDEX

Explanations

mathematical notation and symbols related to sequences and dimensions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

expandindo

-0.72

 estimés

-0.53

γα

-0.52

ագրություններ

-0.51

irme

-0.50

vole

-0.50

={({

-0.49

 pris

-0.48

irus

-0.48

ír

-0.47

POSITIVE LOGITS

cdots

1.00

dots

0.89

ddots

0.87

 CreateTagHelper

0.83

⋱

0.78

 onPostExecute

0.77

⋯

0.75

vdots

0.75

StructEnd

0.73

iastes

0.73

Activations Density 1.521%

mathematical notation and symbols related to sequences and dimensions

No Comments

No Known Activations