INDEX

Explanations

data related to measurements and statistical results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

public

-0.43

 nostri

-0.39

åringen

-0.36

 reú

-0.36

omics

-0.35

 précie

-0.35

trud

-0.34

dez

-0.34

 trasc

-0.34

POSITIVE LOGITS

 respectively

1.19

respectively

1.13

RenderAtEndOf

1.09

adaptiveStyles

1.05

 '\\;'

1.04

posedge

0.95

 respectivamente

0.95

 autorytatywna

0.94

twimg

0.92

Diwedd

0.89

Activations Density 0.803%

data related to measurements and statistical results

No Comments

No Known Activations