INDEX

Explanations

conjunctions and related terms indicating connections or relationships 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 @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

BagConstraints

-0.49

ूरत

-0.45

openqa

-0.45

autogui

-0.44

Vidite

-0.44

udra

-0.43

 suit

-0.43

waitKey

-0.43

AppMethodBeat

-0.43

जब

-0.43

POSITIVE LOGITS

 around

0.94

 AROUND

0.90

 Around

0.84

 alrededor

0.84

 autour

0.83

 intorno

0.81

ofire

0.80

Around

0.78

around

0.77

 kolem

0.76

Activations Density 0.125%

conjunctions and related terms indicating connections or relationships between concepts

No Comments

No Known Activations