INDEX

Explanations

elements related to nodes and relationships in a structured format, similar to graph theory concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Италијани

-0.47

 uſed

-0.45

angliski

-0.44

 becauſe

-0.42

Cyfarwyddwr

-0.42

 الحره

-0.42

 gyhoeddwyd

-0.42

InjectAttribute

-0.42

 Profiling

-0.41

 AssemblyProduct

-0.41

POSITIVE LOGITS

parsedMessage

0.47

endphp

0.42

ItemBackground

0.42

依

0.40

 متعلقه

0.39

CreateInfo

0.38

TryDecodeAsNil

0.38

 himself

0.37

StructEnd

0.37

 تانيه

0.36

Activations Density 0.893%

elements related to nodes and relationships in a structured format, similar to graph theory concepts

No Comments

No Known Activations