INDEX

Explanations

terms and references related to infections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

AsUp

-0.96

:+:

-0.85

 hâte

-0.74

httphttps

-0.74

 referenties

-0.71

Yaz

-0.70

newArrayList

-0.69

YY

-0.68

NSM

-0.68

 Statements

-0.67

POSITIVE LOGITS

 infection

1.57

 infections

1.56

 Infections

1.40

 Infection

1.38

infection

1.25

Infection

1.23

infec

1.23

 infect

1.20

 infected

1.17

infected

1.13

Activations Density 0.165%

terms and references related to infections

No Comments

No Known Activations