INDEX

Explanations

mentions of programs and related entities

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

AlterField

-0.80

 médicaux

-0.80

 larmes

-0.75

createCell

-0.74

putstr

-0.73

 visuales

-0.73

etches

-0.73

ECTS

-0.72

 cheeks

-0.71

 Oxide

-0.70

POSITIVE LOGITS

 program

2.35

 programs

2.34

 programmes

2.13

 programme

2.10

 Program

2.08

 Programs

2.02

program

2.02

Program

2.01

PROGRAM

2.01

Programs

1.97

Activations Density 0.039%

mentions of programs and related entities

No Comments

No Known Activations