INDEX

Explanations

numerical values representing financial magnitudes or consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 تضيفلها

-0.70

ineno

-0.55

Và

-0.53

Yourself

-0.51

://$

-0.49

ocere

-0.49

ROGEN

-0.49

pompa

-0.49

setSubject

-0.49

edos

-0.49

POSITIVE LOGITS

 ComVisible

0.59

 InputDecoration

0.59

+:+

0.57

 shutil

0.57

 remercie

0.56

 >=",

0.56

 nakalista

0.53

yargs

0.52

 cucchiaio

0.52

Autoritní

0.51

Activations Density 0.033%

numerical values representing financial magnitudes or consequences

No Comments

No Known Activations