INDEX

Explanations

definitions and descriptions of devices and equipment

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 OMITBAD

-0.76

 estekak

-0.72

 BoxFit

-0.71

 utafitiHapana

-0.67

verifyException

-0.65

 HFILL

-0.60

MigrationBuilder

-0.59

fillType

-0.58

yntaxException

-0.57

----</

-0.56

POSITIVE LOGITS

lässlich

0.40

Bel

0.35

Street

0.35

River

0.34

ьаж

0.34

 esat

0.33

]")]

0.33

 poichè

0.33

 tør

0.33

mathop

0.33

Activations Density 0.234%

definitions and descriptions of devices and equipment

No Known Activations