INDEX

Explanations

statements related to actions, processes, or recommendations

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

 Vikipedi

-0.70

Diweddarwch

-0.69

AndEndTag

-0.66

逅

-0.64

RectangleBorder

-0.63

GTCX

-0.62

twimg

-0.61

 utafitiHapana

-0.61

withstanding

-0.60

enumi

-0.59

POSITIVE LOGITS

rices

0.53

Waff

0.48

 autorytatywna

0.47

ocardio

0.45

raisemb

0.45

擔

0.44

uxxxx

0.43

tă

0.43

 dica

0.43

imb

0.43

Activations Density 2.413%

statements related to actions, processes, or recommendations

No Comments

No Known Activations