INDEX

Explanations

mathematical notation involving variables and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<eos>

-0.43

/**

-0.42

urably

-0.42

gimento

-0.41

/**

-0.40

("

-0.40

 Brot

-0.40

 caldo

-0.40

 Jérusalem

-0.40

ługa

-0.40

POSITIVE LOGITS

aarrggbb

0.96

HtmlAttribute

0.93

Personendaten

0.92

WithIOException

0.91

IUrlHelper

0.88

帖最后由

0.85

Hauptartikel

0.83

verwijspagina

0.83

rungsseite

0.82

PerformLayout

0.81

Activations Density 0.462%

mathematical notation involving variables and equations

No Comments

No Known Activations