INDEX

Explanations

technical terms and language related to programming and APIs

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

astify

-0.80

enterOuterAlt

-0.68

IntoConstraints

-0.64

Geplaatst

-0.61

 BoxFit

-0.58

DockStyle

-0.58

ربای

-0.56

uestamente

-0.56

spaceBetween

-0.55

hésite

-0.54

POSITIVE LOGITS

pub

0.86

fn

0.82

fn

0.78

pub

0.67

 impl

0.58

impl

0.56

Pub

0.52

#[

0.51

Pub

0.50

PUB

0.48

Activations Density 0.097%

technical terms and language related to programming and APIs

No Comments

No Known Activations