INDEX

Explanations

references to binary data or formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 sagesse

-0.56

 amitié

-0.55

 Abad

-0.54

 sélectionnés

-0.54

 snippetHide

-0.54

UpInside

-0.53

 romantique

-0.53

 Marav

-0.52

 sposa

-0.51

 inégal

-0.51

POSITIVE LOGITS

Sou

1.02

Sou

0.96

sou

0.93

#+#

0.88

SOU

0.81

SOU

0.77

']:

0.74

sou

0.74

"])){

0.72

"){

0.69

Activations Density 0.093%

references to binary data or formats

No Comments

No Known Activations