INDEX

Explanations

references to various entities and their relationships in a network or system context

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

another or other followed by a noun

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

SequentialGroup

-0.63

 surla

-0.55

setupUi

-0.48

findpost

-0.48

Gön

-0.47

Spots

-0.47

Effort

-0.46

뀜

-0.45

 resourceCulture

-0.44

ValueGeneration

-0.43

POSITIVE LOGITS

 other

0.54

other

0.54

 sesama

0.52

 anderen

0.52

 others

0.51

 otros

0.49

autres

0.49

其它

0.49

 innych

0.48

 autres

0.48

Activations Density 0.051%

references to various entities and their relationships in a network or system context

another or other followed by a noun

No Comments

No Known Activations