INDEX

Explanations

references to potential outcomes or impacts

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

rhosis

-0.75

 escuchadas

-0.65

 numberOfRows

-0.64

XtraEditors

-0.62

 Biscuit

-0.59

 Biscuits

-0.59

LError

-0.58

setCellStyle

-0.56

losures

-0.56

 bishops

-0.56

POSITIVE LOGITS

 potential

3.33

Potential

3.12

 Potential

3.09

potential

3.02

 POTENTIAL

2.72

 potencial

2.50

 potentials

2.42

 potensi

2.28

 potentiel

2.24

 potenciales

2.18

Activations Density 0.066%

references to potential outcomes or impacts

No Comments

No Known Activations