INDEX

Explanations

references to lines in graphical representations or documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

atteindre

-0.61

ub

-0.60

 propOrder

-0.59

Από

-0.56

AddWithValue

-0.56

 समीक्षाएं

-0.56

 buhay

-0.56

TextWatcher

-0.54

sobí

-0.54

enumi

-0.54

POSITIVE LOGITS

lines

1.46

LINES

0.99

ines

0.88

Lines

0.81

 outline

0.76

ainville

0.73

LINE

0.72

 lines

0.70

iness

0.70

MessageOf

0.69

Activations Density 0.090%

references to lines in graphical representations or documents

No Comments

No Known Activations