INDEX

Explanations

complex techniques or concepts described through detailed processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

CloseOperation

-0.82

 Jefus

-0.69

Datuak

-0.68

RSpec

-0.64

 فريبيس

-0.63

addGap

-0.62

 themſelves

-0.62

}$

-0.59

 purpoſe

-0.59

ſelf

-0.59

POSITIVE LOGITS

SequentialGroup

0.69

Begriffsklä

0.65

ARIUS

0.60

wherein

0.59

 wherein

0.59

 waarbij

0.58

 whereby

0.57

kdy

0.57

rahat

0.53

autorest

0.52

Activations Density 0.807%

complex techniques or concepts described through detailed processes

No Comments

No Known Activations