INDEX

Explanations

phrases related to processes and approvals within 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 @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 surla

-0.74

########.

-0.59

KeySpec

-0.58

 menyerang

-0.54

 pinulongan

-0.53

 lái

-0.53

UnitTesting

-0.52

})();

-0.50

 storici

-0.48

parity

-0.48

POSITIVE LOGITS

 process

3.35

process

2.88

 Process

2.73

 processes

2.65

Process

2.63

 PROCESS

2.55

 processus

2.48

 proceso

2.46

 processo

2.44

 proses

2.28

Activations Density 0.592%

phrases related to processes and approvals within various contexts

No Comments

No Known Activations