INDEX

Explanations

references to actions or events that occur after a specific condition or task is fulfilled

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

post-installation messages

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 PeEnEo

-0.42

esModule

-0.40

 लेकर

-0.39

hes

-0.38

ungkinan

-0.37

 gebre

-0.36

 Chwiliwch

-0.36

 many

-0.36

posiciones

-0.36

encontra

-0.35

POSITIVE LOGITS

 насељу

0.52

 Wicidata

0.48

 typelib

0.48

tispiece

0.47

 للاسماء

0.45

WebElementEntity

0.44

Sucesor

0.44

клопе

0.44

urangan

0.43

verifyException

0.43

Activations Density 0.002%

references to actions or events that occur after a specific condition or task is fulfilled

post-installation messages

No Comments

No Known Activations