INDEX

Explanations

uses of the word "like" and also the verb "to be"

oai_token-act-pair · gemini-2.0-flash

like

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

KommentareTeilen

-0.72

">//

-0.68

__((

-0.64

ThroughAttribute

-0.63

AccessorTable

-0.61

 initComponents

-0.61

 SwitchCompat

-0.59

WebServlet

-0.58

']=$

-0.57

 становника

-0.53

POSITIVE LOGITS

0.52

 ground

0.50

 paper

0.48

oil

0.48

 draft

0.47

точник

0.47

 Benson

0.46

 gold

0.45

وعة

0.45

 there

0.44

Activations Density 6.160%

uses of the word "like" and also the verb "to be"

like

No Comments

No Known Activations