INDEX

Explanations

mathematical expressions and notations involving matrices or polynomials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 Ross

-0.62

 مرئيه

-0.59

Ross

-0.59

 Camar

-0.58

 Betts

-0.58

Lur

-0.58

 Luis

-0.57

Gin

-0.56

PAC

-0.56

JET

-0.55

POSITIVE LOGITS

lambda

1.38

λ

1.32

λ

1.28

 lambda

1.28

 lamb

0.97

 Lamb

0.88

Lam

0.86

Lamb

0.86

 Lambda

0.85

 Zhao

0.83

Activations Density 0.947%

mathematical expressions and notations involving matrices or polynomials

No Comments

No Known Activations