INDEX

Explanations

mathematical expressions or structured formats involving alignment

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

stur

-0.52

 monit

-0.48

 Howard

-0.46

 biar

-0.45

rou

-0.45

 karbon

-0.44

IVer

-0.44

şti

-0.44

 carbon

-0.44

 glyphicon

-0.43

POSITIVE LOGITS

aligned

1.58

ंदीखरीदारी

0.88

 CURIAM

0.81

 détaillés

0.78

клопе

0.77

MathML

0.77

 AssemblyTitle

0.76

Filmographie

0.76

 numériques

0.75

 soutenu

0.75

Activations Density 0.035%

mathematical expressions or structured formats involving alignment

No Comments

No Known Activations