INDEX

Explanations

phrases that indicate impending actions or decisions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

hyrchwyd

-0.40

grès

-0.39

respon

-0.39

 necesariamente

-0.34

 concentrate

-0.34

 régulièrement

-0.34

spra

-0.34

 Respon

-0.33

 television

-0.32

endregion

-0.32

POSITIVE LOGITS

 verge

0.54

 AssemblyProduct

0.52

Notae

0.52

Autoritní

0.52

 hendak

0.51

 AssemblyTitle

0.51

帖最后由

0.50

AndEndTag

0.49

 GenerationType

0.48

istoitu

0.48

Activations Density 0.426%

phrases that indicate impending actions or decisions

No Known Activations