INDEX

Explanations

exceptions and related system error terms in code

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

getDoctrine

-0.51

 leña

-0.50

 Rabatt

-0.50

Sy

-0.49

 connais

-0.49

osaurus

-0.49

tomcat

-0.48

ھو

-0.48

 défin

-0.48

 Auto

-0.48

POSITIVE LOGITS

ruptedException

0.87

EDEFAULT

0.84

 الرياضيه

0.81

évaluateur

0.80

 ostavi

0.78

AutoScaleMode

0.76

 "..\..\..\

0.75

0.70

 समीक्षक

0.70

 تضيفلها

0.69

Activations Density 0.012%

exceptions and related system error terms in code

No Comments

No Known Activations