INDEX

Explanations

quantitative data and statistics related to users and measurements

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

apimachinery

-0.81

enumii

-0.69

+#+#

-0.64

Хьажоргаш

-0.63

enumi

-0.62

 EconPapers

-0.61

 تضيفلها

-0.57

styleType

-0.57

 архивлан

-0.57

 zvuky

-0.56

POSITIVE LOGITS

 drinking

0.51

どうか

0.50

Quy

0.46

 Drinking

0.45

 equivale

0.45

utete

0.44

 interpreta

0.44

Unnamed

0.42

entor

0.42

setzer

0.42

Activations Density 0.445%

quantitative data and statistics related to users and measurements

No Comments

No Known Activations