INDEX

Explanations

first-person pronouns and indicators of personal opinions

oai_token-act-pair · gemini-2.0-flash

I

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

bukkit

-0.70

awtextra

-0.69

posedge

-0.68

ValueStyle

-0.68

ChildScrollView

-0.67

/***/

-0.67

 createSlice

-0.66

<?

-0.65

WSGI

-0.63

 initComponents

-0.63

POSITIVE LOGITS

 lumineux

0.61

 couverts

0.58

 متعلقه

0.57

 copertura

0.57

 banques

0.56

 bancaire

0.55

 tombé

0.54

 vocale

0.53

 fatica

0.53

 dangereux

0.52

Activations Density 0.711%

first-person pronouns and indicators of personal opinions

I

No Comments

No Known Activations