INDEX

Explanations

technical terms and concepts related to machinery and processes involving text composition and printing

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

 اب

-0.63

 BoxDecoration

-0.61

acteria

-0.57

DispatchToProps

-0.56

 theirs

-0.53

')['

-0.52

irical

-0.52

Hauptartikel

-0.51

naut

-0.51

шу

-0.51

POSITIVE LOGITS

CompleteListener

0.57

 الوا

0.57

PreferredItem

0.56

 episode

0.56

Портали

0.54

ValueStyle

0.54

idamente

0.53

Contribute

0.53

 bevat

0.52

SuppressLint

0.52

Activations Density 0.967%

technical terms and concepts related to machinery and processes involving text composition and printing

No Comments

No Known Activations