INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 reluct

-6.01

 impra

-5.66

 unspeak

-5.62

 shenan

-5.62

 disagre

-5.57

 increa

-5.45

 apprehen

-5.40

 depic

-5.34

 encomp

-5.21

 indestru

-5.16

POSITIVE LOGITS

<bos>

11.33

 Walkover

2.38

expandindo

2.38

GEBURTSDATUM

2.35

 betweenstory

2.29

Autoritní

2.29

 Paglinawan

2.25

 CreateTagHelper

2.15

 '\\;'

2.15

 autorytatywna

2.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.