INDEX

Explanations

code structures related to method definitions and data input processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

AccessorTable

-1.48

WriteBarrier

-1.43

MigrationBuilder

-1.40

]='\

-1.34

Obrázky

-1.30

contentLoaded

-1.29

'])->

-1.27

 unknownFields

-1.27

AddTagHelper

-1.22

ReusableCell

-1.19

POSITIVE LOGITS

↵

0.50

in

0.50

or

0.49

0.43

0.42

to

0.42

0.41

0.40

Activations Density 0.150%

code structures related to method definitions and data input processes

No Comments

No Known Activations