INDEX

Explanations

information about accountability and oversight in 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

 later

-0.40

从此

-0.33

 earlier

-0.32

JK

-0.32

 Influ

-0.31

Linq

-0.31

HIER

-0.30

aspectj

-0.30

 THIS

-0.30

 méta

-0.30

POSITIVE LOGITS

hoeddwyd

0.66

InitVars

0.65

featureID

0.63

Tikang

0.63

principalColumn

0.60

ValueStyle

0.56

 الرياضيه

0.55

хьтан

0.55

ngdoc

0.51

 kasarigan

0.50

Activations Density 1.178%

information about accountability and oversight in processes

No Comments

No Known Activations