INDEX

Explanations

phrases and words indicating tasks, actions, or objectives related to improvement or efficiency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 spéciaux

-0.61

 normaux

-0.59

 actuels

-0.59

 domestiques

-0.56

 enfans

-0.54

Appear

-0.54

 alcanza

-0.54

 alimentaires

-0.53

 seuls

-0.53

 virtuales

-0.52

POSITIVE LOGITS

writeFieldEnd

1.01

:✨

0.88

 himo

0.86

PhysRevD

0.85

 AssemblyTitle

0.83

titleMargin

0.80

PreferredItem

0.80

]),

0.80

modelBuilder

0.78

 يتيمه

0.78

Activations Density 0.748%

phrases and words indicating tasks, actions, or objectives related to improvement or efficiency

No Comments

No Known Activations