INDEX

Explanations

mathematical symbols and notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ことが

-0.33

 bare

-0.32

 should

-0.32

Ded

-0.32

Ded

-0.31

assy

-0.31

Sd

-0.31

 зас

-0.31

ensi

-0.30

 possess

-0.30

POSITIVE LOGITS

Personendaten

0.77

帖最后由

0.76

 kasarigan

0.71

WriteTagHelper

0.65

AddTagHelper

0.64

 betweenstory

0.61

########.

0.61



0.59

الدراسه

0.58

 мәкал

0.58

Activations Density 0.783%

mathematical symbols and notation

No Comments

No Known Activations