INDEX

Explanations

nested parentheses and brackets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

geschäft

-0.65

 nicio

-0.62

Cyfeiriadau

-0.56

</h4>

-0.56

</h5>

-0.53

 kompeti

-0.52

ῖς

-0.50

 ää

-0.50

 سپ

-0.50

 Jesuits

-0.49

POSITIVE LOGITS

новниш

0.89

 AspNetCore

0.68

 LoggerFactory

0.68

 PartialEq

0.67

ksikon

0.64

partimento

0.63

 AssemblyProduct

0.62

 مرئيه

0.60

migrationBuilder

0.60

ఔ

0.59

Activations Density 0.058%

nested parentheses and brackets

No Comments

No Known Activations