INDEX

Explanations

technical terms and references related to processes and specifications in scientific or engineering contexts

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

NewReader

-0.28

 Intent

-0.28

 leal

-0.27

tia

-0.27

 hele

-0.25

 AGENCY

-0.25

feu

-0.25

fer

-0.24

 Basis

-0.24

 EXERCISES

-0.24

POSITIVE LOGITS

tagHelperRunner

0.76

ValueStyle

0.73

 pinulongan

0.68

IntoConstraints

0.60

 kaynağından

0.59

 дописавши

0.58

 utafitiHapana

0.58

elemField

0.57

tonode

0.56

epam

0.56

Activations Density 4.767%

technical terms and references related to processes and specifications in scientific or engineering contexts

No Comments

No Known Activations