INDEX

Explanations

references to configuration and setup processes, particularly in technical contexts related to APIs and data pipelines

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

፩

-0.59

Попис

-0.52

makeText

-0.51

VersionUID

-0.50

DockStyle

-0.49

Rohy

-0.49

 decidi

-0.48

 fuckin

-0.48

kissen

-0.48

nodoc

-0.47

POSITIVE LOGITS

 workaround

0.62

 reproduced

0.60

 reproduce

0.58

 reproducing

0.52

 reproduces

0.48

Regards

0.47

 escalated

0.46

 colleague

0.45

 impacted

0.45

 Reproduce

0.44

Activations Density 0.848%

references to configuration and setup processes, particularly in technical contexts related to APIs and data pipelines

No Known Activations