INDEX

Explanations

patterns or structures in data representations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

تقاوى

-0.73

writeFieldEnd

-0.72

 незавершена

-0.71

Билгалдахарш

-0.69

 CreateTagHelper

-0.69

 kasarigan

-0.67

 estekak

-0.66

Espèce

-0.66

protoimpl

-0.65

 Wikimedijinoj

-0.63

POSITIVE LOGITS

second

0.35

 Económica

0.34

onde

0.32

private

0.32

nd

0.32

another

0.31

 second

0.31

 another

0.31

 holding

0.31

냈

0.30

Activations Density 1.824%

patterns or structures in data representations

No Comments

No Known Activations