INDEX

Explanations

references to direct relationships and effects in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Personensuche

-1.14

 Walkover

-0.90

FailureListener

-0.86

HMM

-0.85

viewDidLoad

-0.81

ueba

-0.79

endpush

-0.78

vespa

-0.77

 Felicia

-0.77

 Kenn

-0.76

POSITIVE LOGITS

 direct

2.37

Direct

2.32

direct

2.25

DIRECT

2.18

 Direct

2.17

 DIRECT

2.03

 directe

1.79

 directa

1.77

 directo

1.76

 directly

1.74

Activations Density 0.090%

references to direct relationships and effects in various contexts

No Comments

No Known Activations