INDEX

Explanations

structured data representations, particularly those resembling tables or data entries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ագրություններ

-0.74

Билгалдахарш

-0.73

Hochspringen

-0.72

LookAnd

-0.70

}\]

-0.70

GraphicsUnit

-0.70

enumii

-0.69

पया

-0.69

 autorytatywna

-0.68

POSITIVE LOGITS

ings

0.48

 lana

0.47

 menthe

0.44

mlu

0.43

ment

0.43

りは

0.42

róleo

0.42

rrr

0.40

 isolato

0.40

Activations Density 0.660%

structured data representations, particularly those resembling tables or data entries

No Comments

No Known Activations