INDEX

Explanations

references to models and model parameters in the text

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

achten

-0.69

IBarButtonItem

-0.69

Чу

-0.68

 fianco

-0.64

 Susie

-0.64

uptime

-0.63

 magnética

-0.63

 Kear

-0.63

 gulp

-0.62

Eup

-0.62

POSITIVE LOGITS

 MODEL

1.77

 model

1.72

 Model

1.72

 models

1.66

model

1.55

 Models

1.53

MODEL

1.53

Models

1.47

Model

1.41

 MODELS

1.37

Activations Density 0.074%

references to models and model parameters in the text

No Comments

No Known Activations