INDEX

Explanations

references to opinions and subjective perceptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

MathML

-0.48

zenta

-0.48

csolódó

-0.48

 väh

-0.46

 quelconque

-0.44

夠

-0.43

 xăm

-0.43

enic

-0.43

cionada

-0.42

brass

-0.42

POSITIVE LOGITS

 opinions

1.36

 opinion

1.36

opinion

1.29

 Opinion

1.24

 Opinions

1.20

opinions

1.16

Opinions

1.14

Opinion

1.10

 opin

0.99

OPINION

0.96

Activations Density 0.161%

references to opinions and subjective perceptions

No Comments

No Known Activations