INDEX

Explanations

references to foundational or key elements of a system, particularly in a structured context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Picchu

-0.80

 Мексичка

-0.79

HasBeenSet

-0.78

iestety

-0.76

زب

-0.75

 Bloomfield

-0.73

 Dutton

-0.73



-0.73

 HasFactory

-0.73

 SDLK

-0.72

POSITIVE LOGITS

 CORE

1.72

 Core

1.68

 core

1.65

core

1.59

 cores

1.56

 Cores

1.50

CORE

1.47

Core

1.47

Cores

1.44

 CoreData

1.23

Activations Density 0.036%

references to foundational or key elements of a system, particularly in a structured context

No Comments

No Known Activations