INDEX

Explanations

transitional phrases indicating the structure of arguments or reasons

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

tr

-0.37

tra

-0.36

pul

-0.35

vox

-0.32

 Trin

-0.32

ze

-0.32

uren

-0.32

TRAD

-0.31

uj

-0.31

 Pear

-0.31

POSITIVE LOGITS

 Réponses

0.63

AutoScaleMode

0.59

 ErrIntOverflow

0.59

enapa

0.58

 defaultstate

0.58

 referrerpolicy

0.58

rungsseite

0.58

 protoimpl

0.57

 kaarangay

0.57

Jeografia

0.57

Activations Density 0.505%

transitional phrases indicating the structure of arguments or reasons

No Comments

No Known Activations