INDEX

Explanations

instances of uncertainty or speculation regarding outcomes and judgments

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bildning

-0.44

AIP

-0.41

SenderId

-0.41

 tadi

-0.41

raa

-0.38

 aseg

-0.37

 advanced

-0.37

lă

-0.37

icef

-0.37

 zosta

-0.36

POSITIVE LOGITS

GEBURTSDATUM

0.97

StoryboardSegue

0.88

awtextra

0.86

RegressionTest

0.84

RectangleBorder

0.77

 oprot

0.76

 estekak

0.75

@"/

0.74

principalTable

0.74

########.

0.71

Activations Density 0.361%

instances of uncertainty or speculation regarding outcomes and judgments

No Comments

No Known Activations