INDEX

Explanations

references to "Saint" and "St" in names or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ་་

-0.89

 leſs

-0.87

 Lyra

-0.87

 uſed

-0.85

/*

-0.84

 ſeveral

-0.83

 Plenum

-0.82

 Manus

-0.80

 perſon

-0.80

deepcopy

-0.80

POSITIVE LOGITS

St

1.58

St

1.45

st

1.39

ST

1.12

 Saint

1.07

st

0.99

 SAINT

0.97

Saint

0.97

 Stur

0.92

 Sankt

0.88

Activations Density 0.060%

references to "Saint" and "St" in names or titles

No Comments

No Known Activations