INDEX

Explanations

specific mathematical notation and expressions, particularly involving formulas and variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 autorytatywna

-1.92

 ―――――

-1.85

 myſelf

-1.80

BibitemShut

-1.77

parsedMessage

-1.73

 Theſe

-1.72

ſelf

-1.71

 purpoſe

-1.68

webElementXpaths

-1.67

)");

-1.67

POSITIVE LOGITS

3.80

2.66

2.43

2.31

2.29

2.20

2.16

2.14

2.10

2.01

Activations Density 1.994%

specific mathematical notation and expressions, particularly involving formulas and variables

No Comments

No Known Activations