INDEX

Explanations

references to success and efficacy 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 @ 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

 سرو

-0.52

 MATTER

-0.52

Addi

-0.51

 Addi

-0.51

ignants

-0.50

 Bourgoin

-0.50

waren

-0.49

 remind

-0.49

ELING

-0.48

 المل

-0.48

POSITIVE LOGITS

 success

1.48

 successes

1.43

 SUCCESS

1.43

 successful

1.37

 Success

1.34

 Successful

1.24

isSuccessful

1.24

successful

1.23

Success

1.23

SUCCESS

1.22

Activations Density 0.117%

references to success and efficacy in various contexts

No Comments

No Known Activations