INDEX

Explanations

phrases indicating procedural or formal requirements, especially in legal or administrative contexts

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

 coraggio

-0.54

 müm

-0.52

 Monfieur

-0.49

 fühlt

-0.48

 secco

-0.48

 unary

-0.48

BOTH

-0.47

 fevere

-0.47

 Horas

-0.46

 juſt

-0.46

POSITIVE LOGITS

AndEndTag

0.91

AddTagHelper

0.84

LookAnd

0.83

__':

0.79

出版年

0.74

ioutil

0.69

__":

0.68

PreferredItem

0.67

Autoritní

0.66

__':

0.64

Activations Density 0.134%

phrases indicating procedural or formal requirements, especially in legal or administrative contexts

No Comments

No Known Activations