INDEX

Explanations

references to specific data points and their significance in various contexts

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

Follows superlatives ("most", "greatest", etc.)

np_acts-logits-general · gemini-2.0-flash

superlative words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

ViewImports

-0.48

enumii

-0.45

Personendaten

-0.42

 Taktlose

-0.41

RemoveField

-0.40

ANTLR

-0.38

GOTREF

-0.38

kloped

-0.37

ampe

-0.37

 snippetHide

-0.37

POSITIVE LOGITS

 가장

2.23

最

2.06

最も

2.05

 most

2.03

 greatest

2.02

 najbardziej

2.00

 strongest

1.99

 largest

1.95

 सबसे

1.92

 biggest

1.89

Activations Density 0.954%

references to specific data points and their significance in various contexts

Follows superlatives ("most", "greatest", etc.)

superlative words

No Comments

No Known Activations