INDEX

Explanations

specific names and references related to authors and academic papers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

Composable

-1.03

 <<<<<<<<<<<<<<

-0.94

Portale

-0.83

 Waffle

-0.83

 Anson

-0.81

andam

-0.77

Ske

-0.75

Anson

-0.74

 protocole

-0.74

-0.73

POSITIVE LOGITS

Azz

0.93

Taz

0.90

########.

0.89

Mox

0.86

 Trix

0.86

Daz

0.85

Kiz

0.85

BoxShadow

0.85

taz

0.84

Bux

0.84

Activations Density 1.820%

specific names and references related to authors and academic papers

No Comments

No Known Activations