INDEX

Explanations

statements related to identity and professional roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 disambiguazione

-0.65

áklad

-0.58

delà

-0.51

PostConstruct

-0.50

jíma

-0.49

 mitz

-0.46

bergh

-0.45

сятся

-0.45

ήσει

-0.43

Bism

-0.43

POSITIVE LOGITS

 springfox

0.73

########.

0.70

endphp

0.69

]--;

0.65

\{\\

0.60

PARE

0.59

SenderId

0.58

apimachinery

0.58

getRuntime

0.57

 Paro

0.56

Activations Density 0.187%

statements related to identity and professional roles

No Comments

No Known Activations