INDEX

Explanations

references to marks or impressions left behind

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

OutOfRange

-0.50

DotNetBar

-0.47

ideae

-0.46

 Over

-0.45

SupportActionBar

-0.44

 وسلم

-0.44

的看着

-0.44

GetProperty

-0.43

 thiệu

-0.43

hips

-0.43

POSITIVE LOGITS

 footprints

1.18

 Footprint

1.14

 footprint

1.13

 huella

1.04

 fingerprint

1.00

 fingerprints

1.00

 Spuren

0.98

 huellas

0.97

 traces

0.88

 trail

0.86

Activations Density 0.280%

references to marks or impressions left behind

No Comments

No Known Activations