INDEX

Explanations

special characters, whitespace, or formatting elements often used in coding or data representation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

neté

-0.56

त्ता

-0.51

pete

-0.44

 понятно

-0.43

 notice

-0.43

ortal

-0.43

ไหน

-0.42

Valentin

-0.41

ตร์

-0.41

ங்கு

-0.41

POSITIVE LOGITS

ArrowToggle

0.86

 Roskov

0.69

principalTable

0.67

#+#

0.65

 Италијани

0.64

 beginnetje

0.64

ыгана

0.64

urlpatterns

0.64

Personensuche

0.62

thâu

0.61

Activations Density 0.819%

special characters, whitespace, or formatting elements often used in coding or data representation

No Comments

No Known Activations