INDEX

Explanations

terms related to data analysis and technology

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

...

-0.51

-0.50

↵

-0.47

set

-0.47

-0.46

cat

-0.46

مصادر

-0.46

..

-0.45

POSITIVE LOGITS

 AssemblyCulture

1.17

WebElementEntity

1.01

IntoConstraints

0.96

 Italijanski

0.92

MENAFN

0.92

IndentedString

0.90

 Monfieur

0.89

 Jefus

0.88

 Beſ

0.88

 Theſe

0.85

Activations Density 1.015%

terms related to data analysis and technology

No Comments

No Known Activations