INDEX

Explanations

technical terms related to datasets, errors, and programming commands

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

Genes, proteins, or cell lines

np_acts-logits-general · gemini-2.0-flash

STAT proteins and gene families

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 kasarigan

-0.73

>{@

-0.71

HtmlAttribute

-0.65

 CreateTagHelper

-0.63

ItemLayout

-0.63

Carriera

-0.60

 utafitiHapana

-0.60

SourceChecksum

-0.59

Mutagenicity

-0.57

ftagPool

-0.56

POSITIVE LOGITS

 series

1.16

 various

0.92

系列

0.91

 family

0.87

series

0.87

 Series

0.85

シリーズ

0.82

various

0.82

 berbagai

0.81

 系列

0.81

Activations Density 1.072%

technical terms related to datasets, errors, and programming commands

Genes, proteins, or cell lines

STAT proteins and gene families

No Comments

No Known Activations