INDEX

Explanations

specific objects or items related to consumer products and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

InputBorder

-1.09

ftagPool

-0.99

出版年

-0.96

RectangleBorder

-0.91

 ModelExpression

-0.90

InjectAttribute

-0.89

Personensuche

-0.88

parsedMessage

-0.87

 ویکی‌پدیا

-0.86

AndEndTag

-0.85

POSITIVE LOGITS

টি

0.46

 itself

0.44

toFloat

0.43

onViewCreated

0.42

 livré

0.42

的所有

0.41

のこと

0.41

 will

0.40

is

0.38

的一切

0.37

Activations Density 0.573%

specific objects or items related to consumer products and their features

No Comments

No Known Activations