INDEX

Explanations

definitions related to programming functions and access modifiers, particularly 'protected' functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Lenn

-0.70

 Frye

-0.67

 Wolver

-0.64

 Gabb

-0.62

 utafitiHapana

-0.60

 Johnnie

-0.59

𝖎

-0.59

 Sapp

-0.58

 apiKey

-0.57

 Jamb

-0.56

POSITIVE LOGITS

 propOrder

1.48

protected

1.30

 protected

0.84

 Protected

0.82

tangentMode

0.80

 PROTECT

0.77

Protected

0.76

 saites

0.74

SequentialGroup

0.72

fillable

0.71

Activations Density 0.018%

definitions related to programming functions and access modifiers, particularly 'protected' functions

No Comments

No Known Activations