INDEX

Explanations

keywords related to understanding complex subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

InstanceState

-0.58

 hesitate

-0.54

vábbi

-0.52

 Référence

-0.51

цездатний

-0.46

hline

-0.46

حياتها

-0.46

nthetic

-0.46

ributions

-0.46

*/),

-0.45

POSITIVE LOGITS

tvguidetime

0.65

 rather

0.60

setVerticalGroup

0.58

 lenker

0.58

帖最后由

0.53

TargetException

0.52

ngdoc

0.51

 esternos

0.51

Jeografia

0.51

 insuffisamment

0.50

Activations Density 1.129%

keywords related to understanding complex subjects

No Comments

No Known Activations