INDEX

Explanations

terms related to procedures and processes

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

 Palis

-0.50

spesies

-0.50

ModelMap

-0.49

 stocking

-0.47

ppins

-0.44

apunov

-0.44

 Sonn

-0.44

 catching

-0.43

 سكانية

-0.43

razine

-0.43

POSITIVE LOGITS

 procedure

1.15

 process

1.13

procedure

1.05

 procedures

1.01

 proceso

0.95

 PROCESS

0.95

 processo

0.95

 procédure

0.95

 Procedure

0.95

process

0.94

Activations Density 0.634%

terms related to procedures and processes

No Comments

No Known Activations