INDEX

Explanations

references to familial or close relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

jų

-0.49

вне

-0.47

estia

-0.46

 rent

-0.45

way

-0.44

 McGrath

-0.43

 Artes

-0.42

讓我們

-0.42

 vuông

-0.41

 fact

-0.41

POSITIVE LOGITS

AndEndTag

1.01

with

0.90

 companions

0.89

 mukana

0.88

 Bersama

0.86

 compagnia

0.85

IndentedString

0.84

 avec

0.83

avec

0.82

DECREF

0.82

Activations Density 0.180%

references to familial or close relationships

No Comments

No Known Activations