INDEX

Explanations

references to various programs and initiatives

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 виправивши

-1.04

 DEFENSE

-0.86

 Defense

-0.82

Defense

-0.79

 defense

-0.78

DoubleQuotes

-0.78

 AssemblyVersion

-0.78

GEBURTSDATUM

-0.75

webElementXpaths

-0.74

 StringTokenizer

-0.71

POSITIVE LOGITS

 programs

0.99

 Programs

0.81

Programs

0.76

 programmes

0.75

programs

0.74

 PROGRAMS

0.72

 programas

0.60

 Injectable

0.56

campal

0.51

 Programmes

0.51

Activations Density 0.114%

references to various programs and initiatives

No Comments

No Known Activations