INDEX

Explanations

prepositions and articles indicating location or positioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

CodeAttribute

-0.67

__*/

-0.66

 Gardner

-0.64

SOUNDBITE

-0.60

 Savage

-0.59

entikan

-0.58

 Standard

-0.57

LETE

-0.57

asts

-0.57

umos

-0.54

POSITIVE LOGITS

 utafitiHapana

0.85

 Linz

0.77

skjaer

0.72

addPreferredGap

0.71

 GLFW

0.71

MessageTagHelper

0.68

 Upan

0.68

 Marlins

0.67

 الحره

0.65

 Shiloh

0.65

Activations Density 0.098%

prepositions and articles indicating location or positioning

No Comments

No Known Activations