INDEX

Explanations

terms related to performance metrics in neural networks

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

entropy or classification

np_acts-logits-general · gemini-2.0-flash

classification labels or scores

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

HtmlAttribute

-0.70

TypedDataSet

-0.58

waffe

-0.56

 demurrer

-0.55

fjspx

-0.54

 IDisposable

-0.53

 InputDecoration

-0.51

 sputnik

-0.51

Демографія

-0.50

parral

-0.48

POSITIVE LOGITS

 labels

0.77

 label

0.72

 softmax

0.67

uxxxx

0.66

 Label

0.65

 Labels

0.65

Labels

0.63

Label

0.63

 LABEL

0.61

label

0.60

Activations Density 0.356%

terms related to performance metrics in neural networks

entropy or classification

classification labels or scores

No Comments

No Known Activations