INDEX

Explanations

references to software components and assemblies in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

tagHelperRunner

-1.09

enumi

-0.99

NameInMap

-0.91

abestanden

-0.90

 consultato

-0.87

DoubleQuotes

-0.87

 unknownFields

-0.86

 nahilalakip

-0.86

 ویکی‌پدیا

-0.86

djangoproject

-0.83

POSITIVE LOGITS

 possible

0.44

tahui

0.44

/}

0.42

datagrid

0.42

 utiles

0.42

穫

0.42

 sécurité

0.41

_=

0.41

">{{$

0.40

 novel

0.40

Activations Density 0.101%

references to software components and assemblies in a technical context

No Comments

No Known Activations