INDEX

Explanations

proper nouns and names related to people, organizations, and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 espírito

-0.46

 file

-0.45

excess

-0.44

kész

-0.43

 Doran

-0.42

期の

-0.42

GINIA

-0.42

 Ranges

-0.41

POSITIVE LOGITS

 Roskov

0.86

featureID

0.83

setVerticalGroup

0.82

 myſelf

0.82

ClientSize

0.81

Климат

0.81

Referències

0.81

 Majefty

0.80

Personendaten

0.78

AndEndTag

0.78

Activations Density 0.180%

proper nouns and names related to people, organizations, and locations

No Comments

No Known Activations