INDEX

Explanations

keywords or indicators related to code or programming functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Drapeau

-0.60

litian

-0.59

wijl

-0.57

 Laplacian

-0.55

 poplar

-0.54

 Weib

-0.53

 stucco

-0.53

Boulder

-0.53

 Landsat

-0.52

 Telerik

-0.52

POSITIVE LOGITS

#![

0.74

Atsauces

0.68

Искәрмәләр

0.68

 SwiftUI

0.66

دانشنامهٔ

0.65

日閲覧

0.65

matchCondition

0.64

::{

0.64

AxisAlignment

0.64

 SPDX

0.63

Activations Density 0.212%

keywords or indicators related to code or programming functionalities

No Comments

No Known Activations