INDEX

Explanations

terms related to software functionality and troubleshooting instructions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.39.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 <>",

-0.52

 ModelExpression

-0.51

 <=",

-0.47

Tembelea

-0.47

extAlignment

-0.47

enterOuterAlt

-0.42

⤹

-0.41

tences

-0.40

={`/

-0.40

basicConfig

-0.40

POSITIVE LOGITS

 uninstall

0.82

 registry

0.75

 Windows

0.75

 Uninstall

0.73

 virus

0.71

 programs

0.71

Uninstall

0.71

 installer

0.71

 executable

0.70

 Registry

0.69

Activations Density 0.743%

terms related to software functionality and troubleshooting instructions

No Known Activations