INDEX

Explanations

references to knowledge and understanding, particularly in a contextual or technical setting

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

 thái

-0.36

ellants

-0.36

 whilst

-0.35

troppo

-0.34

द

-0.34

umerable

-0.33

packets

-0.32

 efforts

-0.32

NotNil

-0.32

IVEREF

-0.32

POSITIVE LOGITS

 AssemblyCompany

0.77

sizeCache

0.64

IntoConstraints

0.60

 ProtoMessage

0.60

 intptr

0.55

parsedMessage

0.52

MessageTagHelper

0.51

 considérons

0.50

сылкі

0.49

ValueStyle

0.48

Activations Density 0.419%

references to knowledge and understanding, particularly in a contextual or technical setting

No Comments

No Known Activations