INDEX

Explanations

nouns and their quantitative descriptors

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

Follows the article "a" or "an"

np_acts-logits-general · gemini-2.0-flash

a before a word

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

ScopeManager

-0.61

 发表于

-0.56

AuthProvider

-0.56

antwoorden

-0.54

ComponentScan

-0.54

rildi

-0.53

engeti

-0.53

 impri

-0.52

copa

-0.52

 kaynağından

-0.51

POSITIVE LOGITS

 another

0.54

 kind

0.50

एक

0.49

 sebuah

0.47

occasione

0.47

EACH

0.46

Iden

0.46

énieurs

0.45

_));

0.45

κέ

0.44

Activations Density 0.388%

nouns and their quantitative descriptors

Follows the article "a" or "an"

a before a word

No Comments

No Known Activations