INDEX

Explanations

references to gradual changes or processes over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

toBeTruthy

-0.46

∃

-0.44

ametro

-0.42

mia

-0.42

toBeDefined

-0.42

Dw

-0.41

bang

-0.40

Usos

-0.39

 ogóle

-0.39

endrait

-0.39

POSITIVE LOGITS

 gradually

2.40

 progressively

2.31

 Gradually

2.23

 gradual

1.86

 slowly

1.85

 increasing

1.79

 progressivement

1.79

 dần

1.79

increasing

1.74

 increasingly

1.74

Activations Density 0.858%

references to gradual changes or processes over time

No Comments

No Known Activations