INDEX

Explanations

activity related to reading, productivity, and personal commitments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 CommonModule

-0.44

ragan

-0.44

dostęp

-0.44

Dis

-0.42

 pierdas

-0.42

ضل

-0.41

binant

-0.41

 Arch

-0.40

telah

-0.40

POSITIVE LOGITS

 AssemblyProduct

0.65

__':

0.65

rungsseite

0.64

tvguidetime

0.64

 liever

0.62

 دیکھیے

0.62

Попис

0.61

ContentAsync

0.61

FormTagHelper

0.60

 linkovi

0.60

Activations Density 0.257%

activity related to reading, productivity, and personal commitments

No Comments

No Known Activations