INDEX

Explanations

phrases and structures related to cellular and biological measurements

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

Follows a period

np_acts-logits-general · gemini-2.0-flash

of

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 auroit

-0.64

 étoit

-0.61

 feroit

-0.60

 pouvoit

-0.59

 ſont

-0.56

 increí

-0.56

 queſta

-0.53

 dévelo

-0.53

 EClass

-0.53

 ſche

-0.52

POSITIVE LOGITS

 literate

0.62

 vaccinated

0.61

 compliant

0.59

 decorated

0.59

 educated

0.54

 tainted

0.53

 partially

0.52

 fully

0.51

 empowered

0.51

 highly

0.50

Activations Density 0.938%

phrases and structures related to cellular and biological measurements

Follows a period

of

No Comments

No Known Activations