INDEX

Explanations

technical and operational criteria related to evaluations and rankings in specific contexts

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

)}</

-0.48

elry

-0.45

OGND

-0.44

Affiliation

-0.43

 Numerade

-0.42

 &___

-0.42

hibli

-0.42

MINOR

-0.42

Équipe

-0.41

vų

-0.41

POSITIVE LOGITS

rrggbb

0.71

 Reſ

0.69

usermodel

0.68

 HasFactory

0.67

 battlefield

0.66

 competition

0.65

Distribuzione

0.63

 where

0.63

yntaxException

0.61

 competencia

0.60

Activations Density 0.839%

technical and operational criteria related to evaluations and rankings in specific contexts

No Comments

No Known Activations