INDEX

Explanations

quantitative terms related to absence or presence in a data context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

-0.68

-0.52

ViewFeatures

-0.48

-0.45

<eos>

-0.44

↵↵

-0.42

and

-0.40

…

-0.40

-0.39

।

-0.39

POSITIVE LOGITS

 Normdatei

1.01

帖最后由

0.89

FunctionFlags

0.88

AccessorTable

0.88

ruff

0.87

Šaltiniai

0.87

IonicModule

0.87

addCriterion

0.86

 Baillargeon

0.86

RectangleBorder

0.85

Activations Density 0.883%

quantitative terms related to absence or presence in a data context

No Comments

No Known Activations