INDEX

Explanations

references to locations or geographical contexts

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

作

-0.54

icz

-0.54

arshan

-0.53

 Waikato

-0.53

 asiento

-0.49

ischer

-0.49

 روسيا

-0.48

Re

-0.47

grine

-0.47

POSITIVE LOGITS

يكب

0.86

ArrowToggle

0.81

PerformLayout

0.77

OGND

0.77

errHandler

0.76

CompleteListener

0.75

contentLoaded

0.75

 ويكيپيديا

0.73

EndInit

0.72

Personensuche

0.72

Activations Density 0.610%

references to locations or geographical contexts

No Comments

No Known Activations