INDEX

Explanations

references to detailed statistical data and results

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Roskov

-0.44

UserScript

-0.41

 ErrIntOverflow

-0.40

leetcode

-0.35

 cref

-0.35

AccessorTable

-0.34

Kariera

-0.34

Distribuzione

-0.32

脚注の使い方

-0.32

 eeuw

-0.32

POSITIVE LOGITS

MigrationBuilder

0.61

 ProtoMessage

0.60

tagHelperRunner

0.57

Personendaten

0.57

SequentialGroup

0.57

 صوتيه

0.53

ViewFeatures

0.52

 propOrder

0.51

Parcelize

0.50

 enfans

0.48

Activations Density 1.755%

references to detailed statistical data and results

No Comments

No Known Activations