INDEX

Explanations

punctuation marks and conversational cues in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Personensuche

-0.88

GEBURTSDATUM

-0.84

jsonwebtoken

-0.80

'):

-0.72

*/;

-0.72

 snippetHide

-0.70

 StatelessWidget

-0.67

urlpatterns

-0.65

 MessageBoxIcon

-0.64

oplayer

-0.64

POSITIVE LOGITS

Alright

1.55

 Alright

1.51

 Okay

1.44

OK

1.44

Okay

1.42

ok

1.41

 okay

1.37

so

1.36

 alright

1.32

So

1.30

Activations Density 0.278%

punctuation marks and conversational cues in text

No Comments

No Known Activations