INDEX

Explanations

numerical data and formatting within text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

opsida

-0.56

 مرئيه

-0.54

PerformLayout

-0.51

 veulent

-0.49

oxidants

-0.47

ാം

-0.47

 estekak

-0.46

createCanvas

-0.46

usercontent

-0.46

tisol

-0.45

POSITIVE LOGITS

ècie

0.58

tvguidetime

0.58

 ControllerBase

0.57

 bilinear

0.57

RenderAtEndOf

0.57

ModelForm

0.55

 AssemblyCulture

0.54

 onCancelled

0.54

 Sando

0.54

 numberOfRows

0.54

Activations Density 0.451%

numerical data and formatting within text

No Comments

No Known Activations