INDEX

Explanations

terms and phrases related to limits, maximums, and restrictions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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



-0.50

évaluateur

-0.49

odils

-0.49

Népesség

-0.48

 تانيه

-0.46

styleType

-0.46

GIVEREF

-0.45

GOTREF

-0.45

‍♀

-0.45

发表于

-0.45

POSITIVE LOGITS

 limit

1.01

 limits

0.87

 limite

0.77

limit

0.76

 Limit

0.71

 limita

0.71

Limit

0.71

 limitation

0.70

limits

0.69

 limites

0.68

Activations Density 0.633%

terms and phrases related to limits, maximums, and restrictions in various contexts

No Comments

No Known Activations