INDEX

Explanations

terms related to both coding syntax and historical references

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

íncia

-0.71

Tikang

-0.62

 Genie

-0.58

})$}

-0.58

-------------</

-0.57

 Psal

-0.56

Genie

-0.56

rokken

-0.55

 remitted

-0.55

 Saludos

-0.55

POSITIVE LOGITS

 Baillargeon

0.76

hu

0.70

Hu

0.61

Lem

0.61

IVEREF

0.60

RegistryLite

0.59

Hu

0.56

Lem

0.56

nan

0.56

Bah

0.55

Activations Density 2.576%

terms related to both coding syntax and historical references

No Comments

No Known Activations