INDEX

Explanations

references to "W" followed by numerical or descriptive data, such as measurements or scientific values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

AutoresizingMask

-0.80

دانشنامهٔ

-0.76

PRNewswire

-0.73

aarrggbb

-0.72

 InputDecoration

-0.72

WindowConstants

-0.71

MLLoader

-0.71

NewUrlParser

-0.69

jsdelivr

-0.68

 صوتيه

-0.67

POSITIVE LOGITS

 Warriors

0.61

первых

0.61

WPS

0.53

 Wednesdays

0.52

Buenas

0.50

稲田

0.49

diali

0.49

 Words

0.49

 bParam

0.48

Activations Density 1.000%

references to "W" followed by numerical or descriptive data, such as measurements or scientific values

No Comments

No Known Activations