INDEX

Explanations

instances of pre-trained components or methods used in programming and machine learning contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

migrationBuilder

-0.60

beginTransaction

-0.58

MessageTagHelper

-0.57

 mourut

-0.57

tagHelperRunner

-0.54

HideFlags

-0.54

featureID

-0.52

 vœux

-0.51

iprot

-0.50

 vực

-0.49

POSITIVE LOGITS

 existing

1.12

 Existing

1.06

Existing

0.99

existing

0.98

 EXISTING

0.86

 preexisting

0.86

 sẵn

0.77

EXIST

0.75

 already

0.75

ALREADY

0.73

Activations Density 0.499%

instances of pre-trained components or methods used in programming and machine learning contexts

No Comments

No Known Activations