INDEX

Explanations

references to literary works and dramatic texts, particularly those by Shakespeare

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Życiorys

-0.59

</tfoot>

-0.59

 Forder

-0.58

//

-0.56

 TextInputType

-0.55

 Saga

-0.49

 Reichs

-0.49

 Krug

-0.48

িনি

-0.47

 estimés

-0.47

POSITIVE LOGITS

 Shakespeare

0.75

 Romeo

0.69

Shakespeare

0.67

 Puck

0.67

 Macbeth

0.67

 Juliet

0.65

Act

0.64

 Mercu

0.63

rrggbb

0.62

 Montague

0.62

Activations Density 0.170%

references to literary works and dramatic texts, particularly those by Shakespeare

No Comments

No Known Activations