INDEX

Explanations

phrases indicating the existence or reference of certain groups, entities, or objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 pouvoirs

-0.78

 Kleidung

-0.62

 épaules

-0.61

 déclarations

-0.61

ropractor

-0.59

 ddelweddau

-0.58

 oreilles

-0.57

adlo

-0.57

 récompenses

-0.56

 gouvernements

-0.56

POSITIVE LOGITS

 guys

0.89

 Theſe

0.83

These

0.77

 beauties

0.76

InitVars

0.76

 autorytatywna

0.73

 kinds

0.73

minecraftforge

0.69

में

0.69

 these

0.69

Activations Density 0.159%

phrases indicating the existence or reference of certain groups, entities, or objects

No Comments

No Known Activations