INDEX

Explanations

recurrences of the word "of."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 dépens

-0.84

 leçons

-0.73

AfterClass

-0.70

 enfans

-0.69

 refusé

-0.67

 Jérusalem

-0.64

 feroit

-0.64

 épaules

-0.62

BooleanField

-0.62

 évêque

-0.62

POSITIVE LOGITS

PreInfinity

0.77

[+]

0.69

 different

0.67

$_['

0.67

 Мексичка

0.66

thâu

0.66

ibouti

0.65

>"+

0.65

encodeWith

0.64

eway

0.63

Activations Density 0.141%

recurrences of the word "of."

No Comments

No Known Activations