INDEX

Explanations

numerical data and comparisons

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

 autorytatywna

-0.60

httphttps

-0.59

 CanadaChoose

-0.59

 defaultstate

-0.57

 intStringLen

-0.51

 marié

-0.50

Personendaten

-0.50

 <=",

-0.49

AndEndTag

-0.49

liosis

-0.48

POSITIVE LOGITS

倍

0.52

 doubling

0.41

 HALF

0.39

//*/

0.39

 half

0.37

 dibanding

0.36

 dibandingkan

0.35

倍

0.35

 halve

0.35

 comparing

0.35

Activations Density 0.557%

numerical data and comparisons

No Comments

No Known Activations