INDEX

Explanations

structured data related to driving and insurance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jsonwebtoken

-0.56

mbolic

-0.50

Transkript

-0.49

vensko

-0.46

 perlahan

-0.46

StreetMap

-0.46

graduates

-0.45

})).

-0.45

一个小

-0.45

niająca

-0.45

POSITIVE LOGITS

 frequency

0.90

 насељу

0.90

 frequ

0.82

 frequent

0.78

frequent

0.73

frequency

0.72

 freq

0.71

 Frequency

0.69

 frequently

0.68

Frequent

0.68

Activations Density 0.388%

structured data related to driving and insurance metrics

No Comments

No Known Activations