INDEX

Explanations

mathematical variables and symbols used in equations

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

findpost

-0.94

boxylic

-0.73

TableAdapter

-0.68

qrst

-0.66

_;

-0.65

'))

-0.64

adhy

-0.63

 BoxFit

-0.63

testify

-0.63

piac

-0.63

POSITIVE LOGITS

MeasureSpec

0.58

 censiti

0.58

 indeterminate

0.47

 tavola

0.44

новниш

0.44

InstanceState

0.43

 iyon

0.41

BeginInit

0.41

 UnityEditor

0.41

Tembelea

0.40

Activations Density 0.811%

mathematical variables and symbols used in equations

No Comments

No Known Activations