INDEX

Explanations

mathematical notation and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ReusableCell

-0.68

ftagPool

-0.61

 doInBackground

-0.61

hoeddwyd

-0.59

inaudible

-0.57

Dichloropropane

-0.56

 master

-0.56

IUrlHelper

-0.55

 Master

-0.53

الحياه

-0.52

POSITIVE LOGITS

 Note

0.95

 note

0.89

Note

0.85

note

0.82

 Thus

0.69

 Notice

0.66

 notice

0.65

 Alternatively

0.64

Notice

0.64

 Intu

0.63

Activations Density 0.903%

mathematical notation and expressions

No Comments

No Known Activations