INDEX

Explanations

personal reflections and opinions on various subjects

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

as

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

InstrumentedTest

-0.63

 AppCompatTheme

-0.51

 Inſ

-0.49

 Reſ

-0.49

 كومونز

-0.48

 Jefus

-0.48

таратура

-0.47

 crimen

-0.47

ſelf

-0.47

 gynhyrchwyd

-0.46

POSITIVE LOGITS

作为

1.73

作為

1.62

as

1.59

 sebagai

1.57

作为一个

1.50

 jako

1.41

身为

1.40

 Sebagai

1.31

 ως

1.27

Sebagai

1.27

Activations Density 0.201%

personal reflections and opinions on various subjects

as

No Known Activations