INDEX

Explanations

references to victimization and injustice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 myſelf

-0.76

 Monfieur

-0.72

 itſelf

-0.62

 Jefus

-0.62

 uſe

-0.59

 klasa

-0.57

 Reſ

-0.57

 Chriftian

-0.57

 uſed

-0.57

 ſeveral

-0.54

POSITIVE LOGITS

 receives

0.95

 receive

0.88

 receiving

0.86

 recevoir

0.83

 received

0.81

received

0.79

 Receives

0.78

receiving

0.76

 Receiving

0.74

 Receive

0.74

Activations Density 0.589%

references to victimization and injustice

No Comments

No Known Activations