INDEX

Explanations

references to intention or intent in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

PerformLayout

-0.76

 חיצוניים

-0.73

bní

-0.69

Hauptartikel

-0.68

 Kats

-0.66

pagos

-0.66

Aar

-0.65

bukkit

-0.65

 років

-0.62

rowy

-0.62

POSITIVE LOGITS

 intention

2.24

 intentions

1.98

 Intention

1.88

intention

1.71

 Inten

1.51

 intención

1.44

 intent

1.41

 inten

1.40

 intenciones

1.35

 intend

1.34

Activations Density 0.051%

references to intention or intent in various contexts

No Comments

No Known Activations