INDEX

Explanations

terms related to scientific measurements and dimensional specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

RegressionTest

-0.40

 noDo

-0.38

transQ

-0.36

posedge

-0.36

værk

-0.35

PCell

-0.34

æn

-0.34

vací

-0.33

힣

-0.32

 InputDecoration

-0.32

POSITIVE LOGITS

AddTagHelper

0.59

 rootReducer

0.58

Portale

0.57

GetAxis

0.56

 CGSize

0.55

OCCURRED

0.55

IntoConstraints

0.55

setVerticalGroup

0.53

 horizontal

0.51

horiz

0.51

Activations Density 0.808%

terms related to scientific measurements and dimensional specifications

No Comments

No Known Activations