INDEX

Explanations

code elements and programming constructs in various contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 kasarigan

-0.84

 الرياضيه

-0.83

Sklici

-0.73

 colgante

-0.70

 colgantes

-0.69

 vectoriales

-0.69

 desmotivaciones

-0.68

 sprzedaży

-0.68

 artesanales

-0.65

 čierna

-0.63

POSITIVE LOGITS

 orient

0.41

妥

0.41

kloped

0.40

Hex

0.40

RET

0.37

Aza

0.36

 Diss

0.35

ori

0.35

tup

0.35

Activations Density 0.850%

code elements and programming constructs in various contexts

No Known Activations