INDEX

Explanations

phrases related to critiques and evaluations of works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 deal

-0.48

样的

-0.47

 invokingState

-0.46

validates

-0.46

DrawerToggle

-0.44

Poids

-0.44

 visual

-0.44

saraba

-0.44

 overall

-0.44

 trade

-0.43

POSITIVE LOGITS

 مشين

0.94

ence

0.88

endphp

0.81

0.76

encia

0.75

ENCE

0.72

__).

0.71

ANCE

0.71

 Gaut

0.70

 ducks

0.69

Activations Density 1.975%

phrases related to critiques and evaluations of works

No Comments

No Known Activations