INDEX

Explanations

descriptors and features related to multi-purpose or versatile items

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

 ObjectParameter

-0.54

 Lightboxes

-0.51

⟬

-0.48

InputTagHelper

-0.47

erstein

-0.47

ikusbot

-0.46

CharacterOffset

-0.45

kward

-0.45

 FormBuilder

-0.44

PerformLayout

-0.44

POSITIVE LOGITS

 living

0.40

 CanadaChoose

0.39

Ideal

0.38

 querr

0.38

 eignet

0.37

 idéale

0.36

 potrze

0.36

 Ideal

0.36

#+#

0.35

 potrzebu

0.35

Activations Density 0.221%

descriptors and features related to multi-purpose or versatile items

No Comments

No Known Activations