INDEX

Explanations

elements related to messaging and update mechanisms in a processing context

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

 kokona

-0.49

 planches

-0.48

 levier

-0.47

 quý

-0.45

 кампа

-0.44

 blending

-0.43

 blend

-0.43

rub

-0.42

 Blend

-0.42

mol

-0.42

POSITIVE LOGITS

 initComponents

0.73

 ddelweddau

0.65

 WebDriverWait

0.65

 Allociné

0.65

Brainz

0.64

 مرئيه

0.64

 jsPsych

0.63

 participating

0.61

RefNanny

0.61

\{\\

0.60

Activations Density 0.467%

elements related to messaging and update mechanisms in a processing context

No Comments

No Known Activations