INDEX

Explanations

phrases and terminology related to theoretical frameworks and their applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ellites

-0.57

Παρα

-0.55

setViewportView

-0.52

profen

-0.52

 imprimée

-0.51

IBarButtonItem

-0.50

makeText

-0.48

 inférieure

-0.48

Vaata

-0.48

hagy

-0.48

POSITIVE LOGITS

 underpin

0.75

InjectAttribute

0.73

InstrumentedTest

0.73

 concepts

0.71

GEBURTSDATUM

0.68

 underlying

0.67

IUrlHelper

0.67

LookAnd

0.65

ResumeLayout

0.65

PerformLayout

0.64

Activations Density 0.181%

phrases and terminology related to theoretical frameworks and their applications

No Comments

No Known Activations