INDEX

Explanations

elements related to specific identifiers or names within a structured context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

الحياه

-0.79

 שוליים

-0.78

 BoxFit

-0.65

ElementException

-0.64

//

-0.63

 للمعارف

-0.62

izoen

-0.62

ViewImports

-0.62

#+#

-0.61

AndEndTag

-0.61

POSITIVE LOGITS

die

0.48

die

0.48

 dies

0.46

FSA

0.45

sow

0.43

sy

0.41

Die

0.41

Die

0.40

 sink

0.40

gely

0.39

Activations Density 0.033%

elements related to specific identifiers or names within a structured context

No Comments

No Known Activations