INDEX

Explanations

references to saints and their associated names and titles

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

Geplaatst

-0.86

κτηρισ

-0.82

 Lyra

-0.81

Anson

-0.80

Kauf

-0.80

 uſed

-0.79

deepcopy

-0.77

enumi

-0.77

__":

-0.77

*/)

-0.77

POSITIVE LOGITS

St

1.30

 Saint

1.20

St

1.15

 SAINT

1.14

Saint

1.09

st

1.06

 saint

0.96

 Sankt

0.95

 Saints

0.93

saint

0.88

Activations Density 0.071%

references to saints and their associated names and titles

No Comments

No Known Activations