INDEX

Explanations

references to threading concepts and terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 HasFactory

-0.66

IntoConstraints

-0.65

BuildContext

-0.63

orith

-0.60

Datuak

-0.59

interop

-0.58

Бахар

-0.58

haup

-0.58

cemment

-0.58

Réalisation

-0.57

POSITIVE LOGITS

 strand

0.77

 strands

0.74

strand

0.71

 Magnet

0.65

Strand

0.62

 Strand

0.61

égard

0.60

 Retrieved

0.58

躇

0.57

 magnet

0.57

Activations Density 0.285%

references to threading concepts and terms

No Comments

No Known Activations