INDEX

Explanations

phrases indicating a relationship or connection between concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

ndham

-0.77

 Rumania

-0.74

 XCTest

-0.73

 Cavendish

-0.73

SSI

-0.71

 Bebe

-0.70

 Pepsi

-0.69

HSC

-0.68

berra

-0.68

 Zeeland

-0.68

POSITIVE LOGITS

 Along

1.31

 ALONG

1.27

Along

1.27

 along

1.19

along

1.09

 langs

0.92

mybatisplus

0.91

 lungo

0.87

 entlang

0.83

AROUND

0.77

Activations Density 0.043%

phrases indicating a relationship or connection between concepts

No Comments

No Known Activations