INDEX

Explanations

patterns related to classification metrics and statistical analysis

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.49

ulico

-0.47

AIRES

-0.42

bag

-0.42

onn

-0.42

map

-0.41

 Spector

-0.41

 druž

-0.40

 even

-0.40

 park

-0.39

POSITIVE LOGITS

ReusableCell

0.87

تقاوى

0.85

SequentialGroup

0.84

StoryboardSegue

0.82

 فريبيس

0.81

principalTable

0.77

SharedCtor

0.77

 الرياضيه

0.74

+#+#

0.72

 Exacts

0.70

Activations Density 0.326%

patterns related to classification metrics and statistical analysis

No Comments

No Known Activations