INDEX

Explanations

programming syntax and structure

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

Units of measurement or symbols

np_acts-logits-general · gemini-2.0-flash

ditto

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

parsedMessage

-0.86

verifyException

-0.86

OGND

-0.77

 autorytatywna

-0.75

aarrggbb

-0.74

 transfieras

-0.73

 kasarigan

-0.72

 defaultstate

-0.69

inSlope

-0.68

TagNumber

-0.68

POSITIVE LOGITS

 similarly

0.38

同じく

0.36

 ditto

0.36

same

0.34

Likewise

0.33

 same

0.33

ditto

0.33

 likewise

0.32

 Likewise

0.30

 SAME

0.30

Activations Density 0.716%

programming syntax and structure

Units of measurement or symbols

ditto

No Comments

No Known Activations