INDEX

Explanations

references to square shapes or geometric configurations

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

Personensuche

-0.84

antd

-0.68

TagMode

-0.62

 Nevis

-0.62

onAttach

-0.57

 ostavi

-0.56

थ

-0.56

editMode

-0.55

IFE

-0.54

şti

-0.53

POSITIVE LOGITS

 square

3.50

 Square

3.31

 SQUARE

3.22

Square

3.16

square

3.04

 squares

2.97

SQUARE

2.90

 Squares

2.74

Squares

2.52

squares

2.35

Activations Density 0.075%

references to square shapes or geometric configurations

No Comments

No Known Activations