INDEX

Explanations

non-zero numerical values or patterns related to numerical data

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

Citations enclosed in brackets

np_acts-logits-general · gemini-2.0-flash

citations and numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

">—

-0.45

 هيا

-0.44

Попис

-0.42

Răsp

-0.41

sträger

-0.41

<bos>

-0.40

 NUKAT

-0.40

HasColumnType

-0.39

 másik

-0.39

rá

-0.39

POSITIVE LOGITS

kloped

0.87

protoimpl

0.80

 Wiktionnaire

0.79

 utafitiHapana

0.72

AnchorStyles

0.72

 OFDb

0.71

 برانيه

0.68

ArrowToggle

0.67

 Offisielt

0.66

enumi

0.65

Activations Density 0.333%

non-zero numerical values or patterns related to numerical data

Citations enclosed in brackets

citations and numbers

No Comments

No Known Activations